US20210356970A1 - Use of a Reference Image to Detect a Road Obstacle - Google Patents
Use of a Reference Image to Detect a Road Obstacle Download PDFInfo
- Publication number
- US20210356970A1 US20210356970A1 US17/391,778 US202117391778A US2021356970A1 US 20210356970 A1 US20210356970 A1 US 20210356970A1 US 202117391778 A US202117391778 A US 202117391778A US 2021356970 A1 US2021356970 A1 US 2021356970A1
- Authority
- US
- United States
- Prior art keywords
- vehicle
- image
- reference image
- road
- computing device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 claims abstract description 62
- 238000011217 control strategy Methods 0.000 claims abstract description 54
- 230000008859 change Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 230000007704 transition Effects 0.000 claims description 8
- 230000033001 locomotion Effects 0.000 claims description 5
- 239000003550 marker Substances 0.000 claims 2
- 238000004891 communication Methods 0.000 description 27
- 230000006870 function Effects 0.000 description 22
- 230000006399 behavior Effects 0.000 description 20
- 230000009471 action Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 9
- 238000001514 detection method Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 230000004927 fusion Effects 0.000 description 6
- 230000002093 peripheral effect Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 239000000446 fuel Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- ATUOYWHBWRKTHZ-UHFFFAOYSA-N Propane Chemical compound CCC ATUOYWHBWRKTHZ-UHFFFAOYSA-N 0.000 description 2
- 238000001069 Raman spectroscopy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000003502 gasoline Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- -1 batteries Substances 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000005057 finger movement Effects 0.000 description 1
- 239000002828 fuel tank Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000010705 motor oil Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000001294 propane Substances 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0248—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G06K9/00805—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D2201/00—Application
- G05D2201/02—Control of position of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Quality & Reliability (AREA)
- Optics & Photonics (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
- The present application is a continuation patent application claiming priority to U.S. patent application Ser. No. 16/896,203 filed Jun. 8, 2020, which is a continuation of U.S. patent application Ser. No. 15/090,089 filed Apr. 4, 2016, which is a continuation of U.S. application Ser. No. 13/613,016 filed Sep. 13, 2012. The contents of these applications are hereby incorporated by reference in their entirety.
- Autonomous vehicles use various computing systems to aid in transporting passengers from one location to another. Some autonomous vehicles may require some initial input or continuous input from an operator, such as a pilot, driver, or passenger. Other systems, for example autopilot systems, may be used only when the system has been engaged, which permits the operator to switch from a manual mode (where the operator exercises a high degree of control over the movement of the vehicle) to an autonomous mode (where the vehicle essentially drives itself) to modes that lie somewhere in between.
- The present application discloses embodiments that relate to use of a reference image to detect a road obstacle. In one aspect, the present application describes a method. The method may comprise receiving, at a computing device configured to control a vehicle, from a camera coupled to the vehicle, an image of a road on which the vehicle is travelling. The computing device may have access to a reference image of the road. The method also may comprise comparing the image to the reference image. The method further may comprise identifying, based on the comparing, a difference between the image and the reference image. The method also may comprise determining a level of confidence for identification of the difference. The method further may comprise modifying, using the computing device, a control strategy associated with a driving behavior of the vehicle, based on the difference and the level of confidence; and controlling, using the computing device, the vehicle based on the modified control strategy.
- In another aspect, the present application describes a non-transitory computer readable medium having stored thereon instructions executable by a computing device to cause the computing device to perform functions. The functions may comprise receiving, from a camera coupled to a vehicle, an image of a road on which the vehicle is travelling. The functions also may comprise comparing the image to a reference image. The functions further may comprise identifying, based on the comparing, a difference between the image and the reference image. The functions also may comprise determining a level of confidence for identification of the difference. The functions further may comprise modifying a control strategy associated with a driving behavior of the vehicle, based on the difference and the level of confidence; and controlling the vehicle based on the modified control strategy.
- In still another aspect, the present application describes a control system for a vehicle. The control system may comprise an image-capture device. The control system also may comprise a computing device in communication with the image capture-device and configured to receive, from the image-capture device, an image of a road on which the vehicle is travelling. The computing device also may be configured to compare the image to a reference image; and identify a difference between the image and the reference image. The computing device further may be configured to determine a level of confidence for identification of the difference. The computing device also may be configured to modify a control strategy associated with a driving behavior of the vehicle, based on the difference and the level of confidence; and control the vehicle based on the modified control strategy.
- The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the figures and the following detailed description.
-
FIG. 1 is a simplified block diagram of an example automobile, in accordance with an example embodiment. -
FIG. 2 illustrates an example automobile, in accordance with an example embodiment. -
FIG. 3 is a flow chart of a method for use of a reference image to detect a road obstacle, in accordance with an example embodiment. -
FIG. 4A illustrates a reference image of a road captured from a first camera pose, in accordance with an example embodiment. -
FIG. 4B illustrates an image of the road captured from a second camera pose, in accordance with an example embodiment. -
FIG. 4C illustrates the image ofFIG. 4B after subtracting background objects depicted in the reference image ofFIG. 4A , in accordance with an example embodiment. -
FIG. 5 is a schematic illustrating a conceptual partial view of a computer program, in accordance with an example embodiment. - The following detailed description describes various features and functions of the disclosed systems and methods with reference to the accompanying figures. In the figures, similar symbols identify similar components, unless context dictates otherwise. The illustrative system and method embodiments described herein are not meant to be limiting. It may be readily understood that certain aspects of the disclosed systems and methods can be arranged and combined in a wide variety of different configurations, all of which are contemplated herein.
- An autonomous vehicle operating on a road may rely on detection of moving objects, obstacles, and road changes for navigation. To facilitate such detection, a computing device, configured to control the vehicle, may be configured to receive, from a camera coupled to the vehicle, an image of the road; and compare the image to a reference image that depicts background objects (e.g., static objects). Based on comparing the image to the reference image, the computing device may be configured to subtract the background objects from the image, and identify a difference between the image and the reference image. The difference, for example, may represent one or more foreground objects such as a moving object, an obstacle, or a road change. The computing device may be configured to determine a level of confidence for identification of the difference. Further, the computing device may be configured to modify a control strategy associated with a driving behavior of the vehicle, based on the difference and the level of confidence; and control the vehicle based on the modified control strategy.
- An example vehicle control system may be implemented in or may take the form of an automobile. Alternatively, a vehicle control system may be implemented in or take the form of other vehicles, such as cars, trucks, motorcycles, buses, boats, airplanes, helicopters, lawn mowers, recreational vehicles, amusement park vehicles, farm equipment, construction equipment, trams, golf carts, trains, and trolleys. Other vehicles are possible as well.
- Further, an example system may take the form of a non-transitory computer-readable medium, which has program instructions stored thereon that are executable by at least one processor to provide the functionality described herein. An example system may also take the form of an automobile or a subsystem of an automobile that includes such a non-transitory computer-readable medium having such program instructions stored thereon.
- Referring now to the Figures,
FIG. 1 is a simplified block diagram of anexample automobile 100, in accordance with an example embodiment. Components coupled to or included in theautomobile 100 may include apropulsion system 102, asensor system 104, acontrol system 106,peripherals 108, apower supply 110, acomputing device 111, and auser interface 112. Thecomputing device 111 may include aprocessor 113, and amemory 114. Thememory 114 may includeinstructions 115 executable by theprocessor 113, and may also storemap data 116. Components of theautomobile 100 may be configured to work in an interconnected fashion with each other and/or with other components coupled to respective systems. For example, thepower supply 110 may provide power to all the components of theautomobile 100. Thecomputing device 111 may be configured to receive information from and control thepropulsion system 102, thesensor system 104, thecontrol system 106, and theperipherals 108. Thecomputing device 111 may be configured to generate a display of images on and receive inputs from theuser interface 112. - In other examples, the
automobile 100 may include more, fewer, or different systems, and each system may include more, fewer, or different components. Additionally, the systems and components shown may be combined or divided in any number of ways. - The
propulsion system 102 may be configured to provide powered motion for theautomobile 100. As shown, thepropulsion system 102 includes an engine/motor 118, anenergy source 120, atransmission 122, and wheels/tires 124. - The engine/
motor 118 may be or include any combination of an internal combustion engine, an electric motor, a steam engine, and a Stirling engine. Other motors and engines are possible as well. In some examples, thepropulsion system 102 could include multiple types of engines and/or motors. For instance, a gas-electric hybrid car could include a gasoline engine and an electric motor. Other examples are possible. - The
energy source 120 may be a source of energy that powers the engine/motor 118 in full or in part. That is, the engine/motor 118 may be configured to convert theenergy source 120 into mechanical energy. Examples ofenergy sources 120 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electrical power. The energy source(s) 120 could additionally or alternatively include any combination of fuel tanks, batteries, capacitors, and/or flywheels. In some examples, theenergy source 120 may provide energy for other systems of theautomobile 100 as well. - The
transmission 122 may be configured to transmit mechanical power from the engine/motor 118 to the wheels/tires 124. To this end, thetransmission 122 may include a gearbox, clutch, differential, drive shafts, and/or other elements. In examples where thetransmission 122 includes drive shafts, the drive shafts could include one or more axles that are configured to be coupled to the wheels/tires 124. - The wheels/
tires 124 ofautomobile 100 could be configured in various formats, including a unicycle, bicycle/motorcycle, tricycle, or car/truck four-wheel format. Other wheel/tire formats are possible as well, such as those including six or more wheels. The wheels/tires 124 ofautomobile 100 may be configured to rotate differentially with respect to other wheels/tires 124. In some examples, the wheels/tires 124 may include at least one wheel that is fixedly attached to thetransmission 122 and at least one tire coupled to a rim of the wheel that could make contact with the driving surface. The wheels/tires 124 may include any combination of metal and rubber, or combination of other materials. - The
propulsion system 102 may additionally or alternatively include components other than those shown. - The
sensor system 104 may include a number of sensors configured to sense information about an environment in which theautomobile 100 is located. As shown, the sensors of the sensor system include a Global Positioning System (GPS)module 126, an inertial measurement unit (IMU) 128, a radio detection and ranging (RADAR)unit 130, a laser rangefinder and/or light detection and ranging (LIDAR)unit 132, acamera 134, andactuators 136 configured to modify a position and/or orientation of the sensors. Thesensor system 104 may include additional sensors as well, including, for example, sensors that monitor internal systems of the automobile 100 (e.g., an 02 monitor, a fuel gauge, an engine oil temperature, etc.). Other sensors are possible as well. - The
GPS module 126 may be any sensor configured to estimate a geographic location of theautomobile 100. To this end, theGPS module 126 may include a transceiver configured to estimate a position of theautomobile 100 with respect to the Earth, based on satellite-based positioning data. In an example, thecomputing device 111 may be configured to use theGPS module 126 in combination with themap data 116 to estimate a location of a lane boundary on road on which theautomobile 100 may be travelling on. TheGPS module 126 may take other forms as well. - The
IMU 128 may be any combination of sensors configured to sense position and orientation changes of theautomobile 100 based on inertial acceleration. In some examples, the combination of sensors may include, for example, accelerometers and gyroscopes. Other combinations of sensors are possible as well. - The
RADAR unit 130 may be considered as an object detection system that may be configured to use radio waves to determine characteristics of the object such as range, altitude, direction, or speed of the object. TheRADAR unit 130 may be configured to transmit pulses of radio waves or microwaves that may bounce off any object in a path of the waves. The object may return a part of energy of the waves to a receiver (e.g., dish or antenna), which may be part of theRADAR unit 130 as well. TheRADAR unit 130 also may be configured to perform digital signal processing of received signals (bouncing off the object) and may be configured to identify the object. - Other systems similar to RADAR have been used in other parts of the electromagnetic spectrum. One example is LIDAR (light detection and ranging), which may be configured to use visible light from lasers rather than radio waves.
- The
LIDAR unit 132 may include a sensor configured to sense or detect objects in an environment in which theautomobile 100 is located using light. Generally, LIDAR is an optical remote sensing technology that can measure distance to, or other properties of, a target by illuminating the target with light. As an example, theLIDAR unit 132 may include a laser source and/or laser scanner configured to emit laser pulses and a detector configured to receive reflections of the laser pulses. For example, theLIDAR unit 132 may include a laser range finder reflected by a rotating mirror, and the laser is scanned around a scene being digitized, in one or two dimensions, gathering distance measurements at specified angle intervals. In examples, theLIDAR unit 132 may include components such as light (e.g., laser) source, scanner and optics, photo-detector and receiver electronics, and position and navigation system. - In an example, The
LIDAR unit 132 may be configured to use ultraviolet (UV), visible, or infrared light to image objects and can be used with a wide range of targets, including non-metallic objects. In one example, a narrow laser beam can be used to map physical features of an object with high resolution. - In examples, wavelengths in a range from about 10 micrometers (infrared) to about 250 nm (UV) could be used. Typically light is reflected via backscattering. Different types of scattering are used for different LIDAR applications, such as Rayleigh scattering, Mie scattering and Raman scattering, as well as fluorescence. Based on different kinds of backscattering, LIDAR can be accordingly called Rayleigh LIDAR, Mie LIDAR, Raman LIDAR and Na/Fe/K Fluorescence LIDAR, as examples. Suitable combinations of wavelengths can allow for remote mapping of objects by looking for wavelength-dependent changes in intensity of reflected signals, for example.
- Three-dimensional (3D) imaging can be achieved using both scanning and non-scanning LIDAR systems. “3D gated viewing laser radar” is an example of a non-scanning laser ranging system that applies a pulsed laser and a fast gated camera. Imaging LIDAR can also be performed using an array of high speed detectors and a modulation sensitive detectors array typically built on single chips using CMOS (complementary metal-oxide-semiconductor) and hybrid CMOS/CCD (charge-coupled device) fabrication techniques. In these devices, each pixel may be processed locally by demodulation or gating at high speed such that the array can be processed to represent an image from a camera. Using this technique, many thousands of pixels may be acquired simultaneously to create a 3D point cloud representing an object or scene being detected by the
LIDAR unit 132. - A point cloud may include a set of vertices in a 3D coordinate system. These vertices may be defined by X, Y, and Z coordinates, for example, and may represent an external surface of an object. The
LIDAR unit 132 may be configured to create the point cloud by measuring a large number of points on the surface of the object, and may output the point cloud as a data file. As the result of a 3D scanning process of the object by theLIDAR unit 132, the point cloud can be used to identify and visualize the object. - In one example, the point cloud can be directly rendered to visualize the object. In another example, the point cloud may be converted to polygon or triangle mesh models through a process that may be referred to as surface reconstruction. Example techniques for converting a point cloud to a 3D surface may include Delaunay triangulation, alpha shapes, and ball pivoting. These techniques include building a network of triangles over existing vertices of the point cloud. Other example techniques may include converting the point cloud into a volumetric distance field and reconstructing an implicit surface so defined through a marching cubes algorithm.
- The
camera 134 may be any camera (e.g., a still camera, a video camera, etc.) configured to capture images of the environment in which theautomobile 100 is located. To this end, the camera may be configured to detect visible light, or may be configured to detect light from other portions of the spectrum, such as infrared or ultraviolet light. Other types of cameras are possible as well. Thecamera 134 may be a two-dimensional detector, or may have a three-dimensional spatial range. In some examples, thecamera 134 may be, for example, a range detector configured to generate a two-dimensional image indicating a distance from thecamera 134 to a number of points in the environment. To this end, thecamera 134 may use one or more range detecting techniques. For example, thecamera 134 may be configured to use a structured light technique in which theautomobile 100 illuminates an object in the environment with a predetermined light pattern, such as a grid or checkerboard pattern and uses thecamera 134 to detect a reflection of the predetermined light pattern off the object. Based on distortions in the reflected light pattern, theautomobile 100 may be configured to determine the distance to the points on the object. The predetermined light pattern may comprise infrared light, or light of another wavelength. - The
actuators 136 may, for example, be configured to modify a position and/or orientation of the sensors. - The
sensor system 104 may additionally or alternatively include components other than those shown. - The
control system 106 may be configured to control operation of theautomobile 100 and its components. To this end, thecontrol system 106 may include asteering unit 138, athrottle 140, abrake unit 142, a sensor fusion algorithm 144, acomputer vision system 146, a navigation or pathingsystem 148, and anobstacle avoidance system 150. - The
steering unit 138 may be any combination of mechanisms configured to adjust the heading or direction of theautomobile 100. - The
throttle 140 may be any combination of mechanisms configured to control the operating speed and acceleration of the engine/motor 118 and, in turn, the speed and acceleration of theautomobile 100. - The
brake unit 142 may be any combination of mechanisms configured to decelerate theautomobile 100. For example, thebrake unit 142 may use friction to slow the wheels/tires 124. As another example, thebrake unit 142 may be configured to be regenerative and convert the kinetic energy of the wheels/tires 124 to electric current. Thebrake unit 142 may take other forms as well. - The sensor fusion algorithm 144 may include an algorithm (or a computer program product storing an algorithm) executable by the
computing device 111, for example. The sensor fusion algorithm 144 may be configured to accept data from thesensor system 104 as an input. The data may include, for example, data representing information sensed at the sensors of thesensor system 104. The sensor fusion algorithm 144 may include, for example, a Kalman filter, a Bayesian network, or another algorithm. The sensor fusion algorithm 144 further may be configured to provide various assessments based on the data from thesensor system 104, including, for example, evaluations of individual objects and/or features in the environment in which theautomobile 100 is located, evaluations of particular situations, and/or evaluations of possible impacts based on particular situations. Other assessments are possible as well - The
computer vision system 146 may be any system configured to process and analyze images captured by thecamera 134 in order to identify objects and/or features in the environment in which theautomobile 100 is located, including, for example, lane information, traffic signals and obstacles. To this end, thecomputer vision system 146 may use an object recognition algorithm, a Structure from Motion (SFM) algorithm, video tracking, or other computer vision techniques. In some examples, thecomputer vision system 146 may additionally be configured to map the environment, track objects, estimate speed of objects, etc. - The navigation and
pathing system 148 may be any system configured to determine a driving path for theautomobile 100. The navigation andpathing system 148 may additionally be configured to update the driving path dynamically while theautomobile 100 is in operation. In some examples, the navigation andpathing system 148 may be configured to incorporate data from the sensor fusion algorithm 144, theGPS module 126, and one or more predetermined maps so as to determine the driving path for theautomobile 100. - The
obstacle avoidance system 150 may be any system configured to identify, evaluate, and avoid or otherwise negotiate obstacles in the environment in which theautomobile 100 is located. - The
control system 106 may additionally or alternatively include components other than those shown. -
Peripherals 108 may be configured to allow theautomobile 100 to interact with external sensors, other automobiles, and/or a user. To this end, theperipherals 108 may include, for example, awireless communication system 152, atouchscreen 154, amicrophone 156, and/or aspeaker 158. - The
wireless communication system 152 may be any system configured to be wirelessly coupled to one or more other automobiles, sensors, or other entities, either directly or via a communication network. To this end, thewireless communication system 152 may include an antenna and a chipset for communicating with the other automobiles, sensors, or other entities either directly or over an air interface. The chipset orwireless communication system 152 in general may be arranged to communicate according to one or more other types of wireless communication (e.g., protocols) such as Bluetooth, communication protocols described in IEEE 802.11 (including any IEEE 802.11 revisions), cellular technology (such as GSM, CDMA, UMTS, EV-DO, WiMAX, or LTE), Zigbee, dedicated short range communications (DSRC), and radio frequency identification (RFID) communications, among other possibilities. Thewireless communication system 152 may take other forms as well. - The
touchscreen 154 may be used by a user to input commands to theautomobile 100. To this end, thetouchscreen 154 may be configured to sense at least one of a position and a movement of a user's finger via capacitive sensing, resistance sensing, or a surface acoustic wave process, among other possibilities. Thetouchscreen 154 may be capable of sensing finger movement in a direction parallel or planar to the touchscreen surface, in a direction normal to the touchscreen surface, or both, and may also be capable of sensing a level of pressure applied to the touchscreen surface. Thetouchscreen 154 may be formed of one or more translucent or transparent insulating layers and one or more translucent or transparent conducting layers. Thetouchscreen 154 may take other forms as well. - The
microphone 156 may be configured to receive audio (e.g., a voice command or other audio input) from a user of theautomobile 100. Similarly, thespeakers 158 may be configured to output audio to the user of theautomobile 100. - The
peripherals 108 may additionally or alternatively include components other than those shown. - The
power supply 110 may be configured to provide power to some or all of the components of theautomobile 100. To this end, thepower supply 110 may include, for example, a rechargeable lithium-ion or lead-acid battery. In some examples, one or more banks of batteries could be configured to provide electrical power. Other power supply materials and configurations are possible as well. In some examples, thepower supply 110 andenergy source 120 may be implemented together, as in some all-electric cars. - The
processor 113 included in thecomputing device 111 may comprise one or more general-purpose processors and/or one or more special-purpose processors (e.g., image processor, digital signal processor, etc.). To the extent that theprocessor 113 includes more than one processor, such processors could work separately or in combination. Thecomputing device 111 may be configured to control functions of theautomobile 100 based on input received through theuser interface 112, for example. - The
memory 114, in turn, may comprise one or more volatile and/or one or more non-volatile storage components, such as optical, magnetic, and/or organic storage, and thememory 114 may be integrated in whole or in part with theprocessor 113. Thememory 114 may contain the instructions 115 (e.g., program logic) executable by theprocessor 113 to execute various automobile functions, including any of the functions or methods described herein. - The components of the
automobile 100 could be configured to work in an interconnected fashion with other components within and/or outside their respective systems. To this end, the components and systems of theautomobile 100 may be communicatively linked together by a system bus, network, and/or other connection mechanism (not shown). - Further, while each of the components and systems is shown to be integrated in the
automobile 100, in some examples, one or more components or systems may be removably mounted on or otherwise connected (mechanically or electrically) to theautomobile 100 using wired or wireless connections. - The
automobile 100 may include one or more elements in addition to or instead of those shown. For example, theautomobile 100 may include one or more additional interfaces and/or power supplies. Other additional components are possible as well. In these examples, thememory 114 may further include instructions executable by theprocessor 113 to control and/or communicate with the additional components. -
FIG. 2 illustrates anexample automobile 200, in accordance with an embodiment. In particular,FIG. 2 shows a Right Side View, Front View, Back View, and Top View of theautomobile 200. Althoughautomobile 200 is illustrated inFIG. 2 as a car, other examples are possible. For instance, theautomobile 200 could represent a truck, a van, a semi-trailer truck, a motorcycle, a golf cart, an off-road vehicle, or a farm vehicle, among other examples. As shown, theautomobile 200 includes afirst sensor unit 202, asecond sensor unit 204, athird sensor unit 206, awireless communication system 208, and acamera 210. - Each of the first, second, and third sensor units 202-206 may include any combination of global positioning system sensors, inertial measurement units, RADAR units, LIDAR units, cameras, lane detection sensors, and acoustic sensors. Other types of sensors are possible as well.
- While the first, second, and
third sensor units 202 are shown to be mounted in particular locations on theautomobile 200, in some examples thesensor unit 202 may be mounted elsewhere on theautomobile 200, either inside or outside theautomobile 200. Further, while only three sensor units are shown, in some examples more or fewer sensor units may be included in theautomobile 200. - In some examples, one or more of the first, second, and third sensor units 202-206 may include one or more movable mounts on which the sensors may be movably mounted. The movable mount may include, for example, a rotating platform. Sensors mounted on the rotating platform could be rotated so that the sensors may obtain information from each direction around the
automobile 200. Alternatively or additionally, the movable mount may include a tilting platform. Sensors mounted on the tilting platform could be tilted within a particular range of angles and/or azimuths so that the sensors may obtain information from a variety of angles. The movable mount may take other forms as well. - Further, in some examples, one or more of the first, second, and third sensor units 202-206 may include one or more actuators configured to adjust the position and/or orientation of sensors in the sensor unit by moving the sensors and/or movable mounts. Example actuators include motors, pneumatic actuators, hydraulic pistons, relays, solenoids, and piezoelectric actuators. Other actuators are possible as well.
- The
wireless communication system 208 may be any system configured to wirelessly couple to one or more other automobiles, sensors, or other entities, either directly or via a communication network as described above with respect to thewireless communication system 152 inFIG. 1 . While thewireless communication system 208 is shown to be positioned on a roof of theautomobile 200, in other examples thewireless communication system 208 could be located, fully or in part, elsewhere. - The
camera 210 may be any camera (e.g., a still camera, a video camera, etc.) configured to capture images of the environment in which theautomobile 200 is located. To this end, thecamera 210 may take any of the forms described above with respect to thecamera 134 inFIG. 1 . While thecamera 210 is shown to be mounted inside a front windshield of theautomobile 200, in other examples thecamera 210 may be mounted elsewhere on theautomobile 200, either inside or outside theautomobile 200. - The
automobile 200 may include one or more other components in addition to or instead of those shown. - A control system of the
automobile 200 may be configured to control theautomobile 200 in accordance with a control strategy from among multiple possible control strategies. The control system may be configured to receive information from sensors coupled to the automobile 200 (on or off the automobile 200), modify the control strategy (and an associated driving behavior) based on the information, and control theautomobile 200 in accordance with the modified control strategy. The control system further may be configured to monitor the information received from the sensors, and continuously evaluate driving conditions; and also may be configured to modify the control strategy and driving behavior based on changes in the driving conditions. -
FIG. 3 is a flow chart of amethod 300 for use of a reference image to detect a road obstacle, in accordance with an example embodiment. - The
method 300 may include one or more operations, functions, or actions as illustrated by one or more of blocks 302-312. Although the blocks are illustrated in a sequential order, these blocks may in some instances be performed in parallel, and/or in a different order than those described herein. Also, the various blocks may be combined into fewer blocks, divided into additional blocks, and/or removed based upon the desired implementation. - In addition, for the
method 300 and other processes and methods disclosed herein, the flowchart shows functionality and operation of one possible implementation of present embodiments. In this regard, each block may represent a module, a segment, or a portion of program code, which includes one or more instructions executable by a processor for implementing specific logical functions or steps in the process. The program code may be stored on any type of computer readable medium or memory, for example, such as a storage device including a disk or hard drive. The computer readable medium may include a non-transitory computer readable medium, for example, such as computer-readable media that stores data for short periods of time like register memory, processor cache and Random Access Memory (RAM). The computer readable medium may also include non-transitory media or memory, such as secondary or persistent long term storage, like read only memory (ROM), optical or magnetic disks, compact-disc read only memory (CD-ROM), for example. The computer readable media may also be any other volatile or non-volatile storage systems. The computer readable medium may be considered a computer readable storage medium, a tangible storage device, or other article of manufacture, for example. - In addition, for the
method 300 and other processes and methods disclosed herein, each block inFIG. 3 may represent circuitry that is wired to perform the specific logical functions in the process. - At
block 302, themethod 300 includes receiving, at a computing device configured to control a vehicle, from a camera coupled to the vehicle, an image of a road on which the vehicle is travelling, and the computing device may have access to a reference image of the road. The computing device may be onboard the vehicle or may be off-board but in wireless communication with the vehicle, for example. Also, the computing device may be configured to control the vehicle in an autonomous or semi-autonomous operation mode. Also, the computing device may be configured to receive, from sensors coupled to the vehicle, information associated with, for example, condition of systems and subsystems of the vehicle, driving conditions, road conditions, etc. Further, a camera, such as thecamera 134 inFIG. 1 or thecamera 210 inFIG. 2 or any other image-capture device, may be coupled to the vehicle and may be in communication with the computing device. The camera may be configured to capture images or video of the road and vicinity of the road on which the vehicle is travelling on. - The reference image may have been captured at a previous time by the vehicle or other vehicles, and may be stored on a memory coupled to the computing device, or may be stored at a remote database (e.g., at a server) in communication with the computing device. The reference image may be an obstacle-free image depicting, for example, background objects (e.g., static objects) on the road or in a vicinity of the road.
- In examples, the reference image may be determined (i.e., constructed or generated) by pre-processing a plurality of source images captured by the vehicle or other vehicles over time. The plurality of source images may or may not have been captured from the same camera pose. A camera pose may refer to a combination of position and orientation of the camera relative to the road. To construct a single reference image from the plurality of source images, the plurality of source images may be merged (e.g., integrated, aligned, matched, overlapped and compared, etc.) to determine the background objects, and generate the reference image depicting the background objects.
- In an example, to merge the plurality of source images, features common to the plurality of source images may be extracted and the background objects may be identified based on the common features. The plurality of source images can then be combined to construct the reference image depicting the background objects.
- In some examples, respective source images of the plurality of source images may be captured at different times, different lighting conditions, or different camera poses; thus, the respective source images may not be matched perfectly. In these examples, the common features and the background object can be determined probabilistically, e.g., a respective accuracy level, which indicates a probability that a respective common feature represents a background object on the road, can be assigned to each of the common features. As an example, a low accuracy level may indicate false identification of a given background object that may be non-existent. Further, the reference image, generated from merging the plurality of source images, may be assigned an accuracy level that is indicative of a degree of accuracy of the reference image in depicting the road and the background objects on the road; in other words, the accuracy level assigned to the reference image may be indicative of robustness of estimating the background objects on the road using the reference image.
- At
block 304, themethod 300 includes comparing the image to the reference image. To detect an obstacle on the road, the computing device may be configured to compare the image captured at a current location of the vehicle to a corresponding reference image. In examples, the computing device may be configured to identify the reference image corresponding to the image captured at the current location of the vehicle based on the current location and orientation of the vehicle. For instance, a Global Position System (GPS) module may be coupled to the vehicle and may be configured to provide, to the computing device, location information relating to a current geographic location (i.e., with respect to the Earth, using satellite-based positioning data) of the vehicle on the road. Based on the location information, the computing device may be configured to determine latitude and longitude of the current geographic location of the vehicle. Additionally or alternatively, an Inertial Measurement Unit (IMU) may be coupled to the vehicle and may be configured to provide to the computing device orientation information associated with position and orientation changes (e.g., yaw angle) of the vehicle based on inertial acceleration. Based on the location information and orientation information, the computing device may be configured to identify the reference image, or a portion of a given reference image, corresponding to the image captured at the current location of the vehicle. - Comparing a first image to a second image may be done effectively in applications where a given camera capturing the first and second images has fixed position. A vehicle, however, is a moving platform. In an example, an image captured by a camera coupled to and moving with the vehicle may not match the reference image depicting the background objects, since the image and the reference image may not have been captured from the same camera pose or lighting condition. Therefore, comparing the image to the reference image in this case may require more computational processing of the image and/or the reference image than in the case of images captured by a fixed camera.
- In some examples, the image may be captured while the vehicle is moving at a certain speed; however, the reference image may have been captured by the vehicle or other vehicles while moving at a different speed. In these examples, the computing device may be configured to identify a frame in a sequence of reference images (or a video) that correspond to a frame in a sequence of images (or a video) captured at a current location of the vehicle taking into account the difference in speed.
- For instance, the vehicle that may have captured the reference sequence of images may have been moving at a first speed, while the vehicle currently capturing the sequence of images at the current location of the vehicle may be moving at a second speed. Based on a respective speed of a respective vehicle, a period of time taken by the vehicle that captured the reference sequence of images to drive over a given portion of the road may be different than a respective period of time taken by the vehicle currently capturing the sequence of images to drive over the given portion of the road. Also, the camera may be capturing images at a certain rate, i.e., a certain number of frames per second. In this manner, for the given portion of the road, a number of frames in the reference sequence of images may be different from a respective number of frames in the sequence of images currently being captured.
- The computing device may thus be configured to compensate for such difference in vehicle dynamics (e.g., compensate for a difference between the first and second speeds) and identify a reference frame corresponding to a given frame captured at the given location of the vehicle. For example, the reference sequence of images may be tagged with speed or dynamic characteristics of the vehicle capturing the reference sequence of images. Based on the difference in vehicle dynamics and the rate of capturing frames, the computing device may be configured to determine the corresponding reference frame that may have been captured at a nearest position to that of the frame captured at the current location of the vehicle.
- In still other examples, the image and the reference image may be misaligned, i.e., the image and the reference image may not be spatially properly aligned. For example, the image may be translated (shifted) or rotated with respect to the corresponding reference image. Such misalignment may preclude the computing device from identifying obstacles on the road. Additionally or alternatively, because of misalignment, the computing device may falsely identify portions of the image as obstacles, while the portions may not represent actual existent obstacles.
- Several factors may cause spatial misalignment between the image and the corresponding reference image. For example, the image may be captured from a given camera pose (e.g., a combination of position and orientation of the image-capture device relative to the road), while the reference image may have been captured from another vehicle and/or from a different camera pose. This difference in camera pose may impede alignment of the image with the reference image.
-
FIG. 4A illustrates areference image 402 of the road captured from a first camera pose, in accordance with an example embodiment, andFIG. 4B illustrates animage 404 of the road captured from a second camera pose, in accordance with an example embodiment. Thereference image 402 depicts background objects such astraffic sign 406, building 408, andlane markers image 404 depicts the background objects in addition to avehicle 412. Thereference image 402 is captured from the first camera pose that is different from the second camera pose from which theimage 404 is captured.FIG. 4B illustrates that theimage 404 is shifted, as an example, compared to thereference image 402 inFIG. 4A . The shift may have been caused by the difference in camera pose, i.e., the vehicle or the image-capture device used to capture thereference image 402 may have been shifted relative to the road compared to the vehicle or the image-capture device used to capture theimage 404. - In order to facilitate comparison of the
image 404 to thereference image 402 and detection of actual obstacles on the road, the computing device may be configured to align theimage 404 with thereference image 402. In one example, to align theimage 404 with thereference image 402, the computing device may be configured to determine a transform that, when applied to pixels of theimage 404 or pixels of thereference image 402, may cause the respective image to shift and/or rotate, and thus cause theimage 404 to be aligned with thereference image 402. - In another example, the computing device may be configured to determine an object in the
image 404 and a corresponding object in thereference image 402. Based on a difference in location of the object in theimage 404 with respect to location of the corresponding object in thereference image 402, the computing device may be configured to determine the transform. In still another example, the computing device may be configured to infer respective camera poses from which theimage 404 and thereference image 402 have been captured, and based on a difference in the respective camera poses, the computing device may be configured to determine the transform. - As an example for illustration, a pixel in the
reference image 404 may be denoted by a vector representing two coordinates of a location of the pixel in two-dimensional space (X and Y). The transform, for example, may include a matrix with elements of the matrix being a function of shift (translation in either X or Y or both) and/or rotation of thereference image 402 relative to theimage 404, for example. When the transform (i.e., the matrix) is applied to the pixel, the pixel is spatially aligned to a corresponding pixel in theimage 404. Thus, when the transform is applied to pixels of thereference image 402, thereference image 402 may be aligned with theimage 404, i.e., application of the transform may compensate for the shift and/or rotation. - Referring back to
FIG. 3 , atblock 306, themethod 300 includes identifying, based on the comparing, a difference between the image and the reference image. After determining the reference image corresponding to the image and, in some instances, aligning the reference image with the image, the computing device may be configured to compare the image to the reference image to determine obstacles on the road. For example, the computing device may be configured to subtract, from the image, background objects depicted in the reference image to determine foreground objects such as a moving object, an obstacle, or a road change. -
FIG. 4C illustrates theimage 404 ofFIG. 4B after subtracting the background objects depicted in thereference image 402 ofFIG. 4A , in accordance with an example embodiment.FIG. 4C shows animage 414 that may be obtained by aligning theimage 404 with thereference image 402 and subtracting the background objects, such as thetraffic sign 406, thebuilding 408, and thelane markers 410A-C, from theimage 404. In this manner, the computing device may be configured to determine a foreground object such as thevehicle 412. AlthoughFIG. 4C depicts road surface after subtracting background objects, in some examples the road surface may be subtracted as a background object as well. - Referring back to
FIG. 3 , atblock 308, themethod 300 includes determining a level of confidence for identification of the difference. As described above, the reference image may be determined based on merging several source images and may be assigned an accuracy level indicative of a level of accuracy of the reference image in depicting the background object or the road. Furthermore, differences in lighting conditions and respective camera poses between the image and the reference image may cause imperfect matching of the image to the reference image. Therefore, in addition to identifying a given difference between the image and the reference image, a level of confidence can be assigned to identification of the difference. The computing device may be configured to determine the level of confidence based on the accuracy level assigned to the reference image and also based on differences in lighting conditions and respective camera pose, or any other factor, between the image and the reference image. In examples, the level of confidence may be associated with identification of the difference and/or identification of a type of the difference (e.g., a type of obstacle represented by the difference such as whether the difference is a moving object, a road change, etc.). - In one example, if the accuracy level assigned to the reference image is high, the computing device may be able to accurately subtract the background object to identify the difference with a high level of confidence. In this example, the computing device may be configured to modify the image (e.g., increase intensity of pixels representing the difference) to more accurately determine nature of the difference or what type of an obstacle is represented by the difference. In contrast, if the accuracy level assigned to the reference image is low, the computing device may not be able to accurately determine and subtract the background object. In such an instance, the computing device may be configured to assign a low level of confidence to an identified difference between the image and the reference image.
- In another example, the computing device may be configured to determine a clarity metric for an identified difference. The clarity metric, for example, may be a function of clarity of the difference between the image and the reference image, or a function of intensity of pixels representing the difference. The level of confidence may be a function of the clarity metric, for example.
- In still another example, the computing device may be configured to identify the difference and determine features such as geometry, boundary, etc., to estimate an obstacle represented by the difference. In some examples, the difference may represent an actual obstacle; however, in other examples, the difference may arise from tree shadows or lens flare of the image-capture device, etc. The computing device may be configured to use a probabilistic model (e.g., a Gaussian distribution) to model uncertainty of estimated geometries and boundaries. Further, the computing device may be configured to determine or assign the level of confidence for the estimation based on the probability model. Thus, the level of confidence may be based on a probability that a respective difference represents an actual obstacle. As an example, a low level of confidence may indicate a high probability of false identification of a given obstacle that may be non-existent.
- In another example, the computing device may be configured to generate a probabilistic model (e.g., a Gaussian distribution), based on information relating to identifying of the difference, to determine the level of confidence. For example, the level of confidence may be determined as a function of a set of parameter values that are determined based on the features associated with the identified difference between the image and the reference image. In this example, the level of confidence may be defined as equal to the probability of an observed outcome (existence of a difference and/or the type of the difference) given those parameter values.
- The level of confidence could be expressed qualitatively, such as a “low,” “medium,” or “high” level of confidence. Alternatively, the level of confidence could be expressed quantitatively, such as a number on a scale. Other examples are possible.
- At
block 310, themethod 300 includes modifying, using the computing device, a control strategy associated with a driving behavior of the vehicle, based on the difference and the level of confidence. The control system of the vehicle may support multiple control strategies and associated driving behaviors that may be predetermined or adaptive to changes in a driving environment of the vehicle. Generally, a control strategy may comprise sets of rules associated with traffic interactions in various driving contexts such as approaching an obstacle (e.g., another vehicle, an accident site, road changes, etc.). The control strategy may comprise rules that determine a speed of the vehicle and a lane that the vehicle may travel on while taking into account safety and traffic rules and concerns (e.g., changes in road geometry, vehicles stopped at an intersection and windows-of-opportunity in yield situation, lane tracking, speed control, distance from other vehicles on the road, passing other vehicles, and queuing in stop-and-go traffic, and avoiding areas that may result in unsafe behavior such as oncoming-traffic lanes, etc.). For instance, in approaching an obstacle, the computing device may be configured to modify or select, based on the identified obstacle and the level of confidence, a control strategy comprising rules for actions that control the vehicle speed to safely maintain a distance with other objects and select a lane that is considered safest given the existence of the obstacle. - As an example, in
FIGS. 4A-4C , if the level of confidence assigned to identification of thevehicle 412 as a difference between the image and the reference image is high (e.g., exceeds a predetermined threshold), the computing device may be configured to utilize sensor information to track thevehicle 412 and make navigation decisions based on driving behavior of thevehicle 412. - In an example, a first control strategy may comprise a default driving behavior and a second control strategy may comprise a defensive driving behavior. Characteristics of a the defensive driving behavior may comprise, for example, following another vehicle maintaining a predetermined safe distance with the other vehicle that may be larger than a distance maintained in the default driving behavior, turning-on lights, reducing a speed of the vehicle, or stopping the vehicle. In this example, the computing device may have identified an obstacle (e.g., an accident site) and may be configured to compare the determined level of confidence of identification of the obstacle to a threshold level of confidence, and the computing device may be configured to select the first or the second control strategy, based on the comparison. For example, if the determined level of confidence is greater than the threshold, the computing device may be configured to select the second driving behavior (e.g., the defensive driving behavior). If the determined level of confidence is less than the threshold, the computing device may be configured to modify the control strategy to the first control strategy (e.g., select the default driving behavior).
- In yet another example, alternatively or in addition to transition between discrete control strategies (e.g., the first control strategy and the second control strategy) the computing device may be configured to select from a continuum of driving modes or states based on the determined level of confidence. In still another example, the computing device may be configured to select a discrete control strategy and also may be configured to select a driving mode from a continuum of driving modes within the selected discrete control strategy. In this example, a given control strategy may comprise multiple sets of driving rules, where a set of driving rules describe actions for control of speed and direction of the vehicle. The computing device further may be configured to cause a smooth transition from a given set of driving rules to another set of driving rules of the multiple sets of driving rules, based on a type of the identified difference (e.g., vehicle, static object, accident site, road changes, etc.) and the level of confidence. A smooth transition may indicate that the transition from the given set of rules to another may not be perceived by a passenger in the vehicle as a sudden or jerky change in a speed or direction of the vehicle, for example.
- In an example, a given control strategy may comprise a program or computer instructions that characterize actuators controlling the vehicle (e.g., throttle, steering gear, brake, accelerator, or transmission shifter) based on the determined level of confidence. The given control strategy may include action sets ranked by priority, and the action sets may include alternative actions that the vehicle may take to accomplish a task (e.g., driving from one location to another). The alternative actions may be ranked based on the identified difference between the image and the reference image (e.g., based on a type of obstacle identified), and the level of confidence of the identification, for example. Also, the computing device may be configured to select an action to be performed and, optionally, modified based on the level of confidence.
- In another example, multiple control strategies (e.g., programs) may continuously propose actions to the computing device. The computing device may be configured to decide which strategy may be selected or may be configured to modify the control strategy based on a weighted set of goals (safety, speed, etc.), for example. Weights of the weighted set of goals may be a function of the type of the identified difference and/or the level of confidence. Based on an evaluation of the weighted set of goals, the computing device, for example, may be configured to rank the multiple control strategies and respective action sets and select or modify a given strategy and a respective action set based on the ranking.
- These examples and driving situations are for illustration only. Other examples and control strategies and driving behaviors are possible as well.
- Referring back to
FIG. 3 , atblock 312, themethod 300 includes controlling, using the computing device, the vehicle based on the modified control strategy. In an example, the computing device may be configured to control actuators of the vehicle using an action set or rule set associated with the modified control strategy. For instance, the computing device may be configured to adjust translational velocity, or rotational velocity, or both, of the vehicle based on the modified driving behavior. As an example, referring toFIGS. 4A-4C , based on identifying thevehicle 412 with a high level of confidence, the computing device may be configured to cause the vehicle controlled by the computing device to follow thevehicle 412, while maintaining a predetermined safe distance with thevehicle 412. - In another example, the computing device may have detected an obstacle (e.g., a stopped vehicle or an accident site) based on a comparison of the
image 404 to thereference image 402, and may have determined a high level of confidence for the identification. In this example, the computing device may be configured to control the vehicle according to a defensive driving behavior to safely navigate around the obstacle. For instance, the computing device may be configured to reduce speed of the vehicle, cause the vehicle to change lanes, and/or shift to a position behind and follow another vehicle while keeping a predetermined safe distance. - These control actions and driving situations are for illustration only. Other actions and situations are possible as well. In one example, the computing device may be configured to control the vehicle based on the modified control strategy as an interim control until a human driver can take control of the vehicle.
- In some embodiments, the disclosed methods may be implemented as computer program instructions encoded on a computer-readable storage media in a machine-readable format, or on other non-transitory media or articles of manufacture.
FIG. 5 is a schematic illustrating a conceptual partial view of an examplecomputer program product 500 that includes a computer program for executing a computer process on a computing device, arranged according to at least some embodiments presented herein. In one embodiment, the examplecomputer program product 500 is provided using a signal bearing medium 501. The signal bearing medium 501 may include one ormore program instructions 502 that, when executed by one or more processors (e.g.,processor 113 in the computing device 111) may provide functionality or portions of the functionality described above with respect toFIGS. 1-4 . Thus, for example, referring to the embodiments shown inFIG. 3 , one or more features of blocks 302-312 may be undertaken by one or more instructions associated with the signal bearing medium 501. In addition, theprogram instructions 502 inFIG. 5 describe example instructions as well. - In some examples, the signal bearing medium 501 may encompass a computer-
readable medium 503, such as, but not limited to, a hard disk drive, a Compact Disc (CD), a Digital Video Disk (DVD), a digital tape, memory, etc. In some implementations, the signal bearing medium 501 may encompass acomputer recordable medium 504, such as, but not limited to, memory, read/write (R/W) CDs, R/W DVDs, etc. In some implementations, the signal bearing medium 501 may encompass acommunications medium 505, such as, but not limited to, a digital and/or an analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.). Thus, for example, the signal bearing medium 501 may be conveyed by a wireless form of the communications medium 505 (e.g., a wireless communications medium conforming to the IEEE 802.11 standard or other transmission protocol). - The one or
more programming instructions 502 may be, for example, computer executable and/or logic implemented instructions. In some examples, a computing device such as the computing device described with respect toFIGS. 1-4 may be configured to provide various operations, functions, or actions in response to theprogramming instructions 502 conveyed to the computing device by one or more of the computerreadable medium 503, thecomputer recordable medium 504, and/or thecommunications medium 505. It should be understood that arrangements described herein are for purposes of example only. As such, those skilled in the art will appreciate that other arrangements and other elements (e.g. machines, interfaces, functions, orders, and groupings of functions, etc.) can be used instead, and some elements may be omitted altogether according to the desired results. Further, many of the elements that are described are functional entities that may be implemented as discrete or distributed components or in conjunction with other components, in any suitable combination and location. - While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope being indicated by the following claims, along with the full scope of equivalents to which such claims are entitled. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting.
Claims (20)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/391,778 US20210356970A1 (en) | 2012-09-13 | 2021-08-02 | Use of a Reference Image to Detect a Road Obstacle |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201213613016A | 2012-09-13 | 2012-09-13 | |
US15/090,089 US10678259B1 (en) | 2012-09-13 | 2016-04-04 | Use of a reference image to detect a road obstacle |
US16/896,203 US11079768B2 (en) | 2012-09-13 | 2020-06-08 | Use of a reference image to detect a road obstacle |
US17/391,778 US20210356970A1 (en) | 2012-09-13 | 2021-08-02 | Use of a Reference Image to Detect a Road Obstacle |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/896,203 Continuation US11079768B2 (en) | 2012-09-13 | 2020-06-08 | Use of a reference image to detect a road obstacle |
Publications (1)
Publication Number | Publication Date |
---|---|
US20210356970A1 true US20210356970A1 (en) | 2021-11-18 |
Family
ID=70973003
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/090,089 Active 2032-11-28 US10678259B1 (en) | 2012-09-13 | 2016-04-04 | Use of a reference image to detect a road obstacle |
US16/896,203 Active US11079768B2 (en) | 2012-09-13 | 2020-06-08 | Use of a reference image to detect a road obstacle |
US17/391,778 Pending US20210356970A1 (en) | 2012-09-13 | 2021-08-02 | Use of a Reference Image to Detect a Road Obstacle |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/090,089 Active 2032-11-28 US10678259B1 (en) | 2012-09-13 | 2016-04-04 | Use of a reference image to detect a road obstacle |
US16/896,203 Active US11079768B2 (en) | 2012-09-13 | 2020-06-08 | Use of a reference image to detect a road obstacle |
Country Status (1)
Country | Link |
---|---|
US (3) | US10678259B1 (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9495874B1 (en) * | 2012-04-13 | 2016-11-15 | Google Inc. | Automated system and method for modeling the behavior of vehicles and other agents |
DE102016205339A1 (en) * | 2016-03-31 | 2017-10-05 | Siemens Aktiengesellschaft | Method and system for detecting obstacles in a danger area in front of a rail vehicle |
US11055532B2 (en) * | 2018-05-02 | 2021-07-06 | Faro Technologies, Inc. | System and method of representing and tracking time-based information in two-dimensional building documentation |
CN112654841A (en) * | 2018-07-06 | 2021-04-13 | 云海智行股份有限公司 | System, method and apparatus for calibrating a sensor mounted on a device |
US11580687B2 (en) * | 2018-12-04 | 2023-02-14 | Ottopia Technologies Ltd. | Transferring data from autonomous vehicles |
US11501478B2 (en) | 2020-08-17 | 2022-11-15 | Faro Technologies, Inc. | System and method of automatic room segmentation for two-dimensional laser floorplans |
JP7427615B2 (en) * | 2021-01-04 | 2024-02-05 | 株式会社東芝 | Information processing device, information processing method and program |
US11102381B1 (en) | 2021-01-05 | 2021-08-24 | Board Of Regents, The University Of Texas System Clearcam Inc. | Methods, systems and controllers for facilitating cleaning of an imaging element of an imaging device |
CN115496978B (en) * | 2022-09-14 | 2023-04-07 | 北京化工大学 | Image and vehicle speed information fused driving behavior classification method and device |
KR102561566B1 (en) * | 2023-02-08 | 2023-08-01 | 주식회사 지성이엔지 | Artificial Intelligence- based video surveillance system and method |
Citations (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5847755A (en) * | 1995-01-17 | 1998-12-08 | Sarnoff Corporation | Method and apparatus for detecting object movement within an image sequence |
US6151539A (en) * | 1997-11-03 | 2000-11-21 | Volkswagen Ag | Autonomous vehicle arrangement and method for controlling an autonomous vehicle |
US20040090117A1 (en) * | 2000-07-26 | 2004-05-13 | Ingo Dudeck | Automatic brake and steering system and method for a vehicle |
US20040126014A1 (en) * | 2002-12-31 | 2004-07-01 | Lipton Alan J. | Video scene background maintenance using statistical pixel modeling |
US20040151342A1 (en) * | 2003-01-30 | 2004-08-05 | Venetianer Peter L. | Video scene background maintenance using change detection and classification |
US20050165550A1 (en) * | 2004-01-23 | 2005-07-28 | Ryuzo Okada | Obstacle detection apparatus and a method therefor |
US20050278088A1 (en) * | 2004-05-29 | 2005-12-15 | Craig Thorner | Method and apparatus for collision avoidance and enhanced visibility in vehicles |
US7327855B1 (en) * | 2001-06-20 | 2008-02-05 | Hrl Laboratories, Llc | Vision-based highway overhead structure detection system |
US20080059007A1 (en) * | 2006-06-09 | 2008-03-06 | Whittaker William L | System and method for autonomously convoying vehicles |
US20080239078A1 (en) * | 2006-11-21 | 2008-10-02 | Harman Becker Automotive Systems Gmbh | Video image presentation system |
US20090028388A1 (en) * | 2007-07-24 | 2009-01-29 | Nec Electronics Corporation | On-vehicle image processing apparatus |
US20090135065A1 (en) * | 2006-02-24 | 2009-05-28 | Toyota Jidosha Kabushiki Kaisha | Object Detecting Apparatus and Method for Detecting an Object |
US20090140887A1 (en) * | 2007-11-29 | 2009-06-04 | Breed David S | Mapping Techniques Using Probe Vehicles |
US20100034423A1 (en) * | 2008-08-06 | 2010-02-11 | Tao Zhao | System and method for detecting and tracking an object of interest in spatio-temporal space |
US20100110193A1 (en) * | 2007-01-12 | 2010-05-06 | Sachio Kobayashi | Lane recognition device, vehicle, lane recognition method, and lane recognition program |
US20100165102A1 (en) * | 2008-12-30 | 2010-07-01 | Hella Kgaa Hueck & Co. | Method and device for determining a change in the pitch angle of a camera of a vehicle |
US7920959B1 (en) * | 2005-05-01 | 2011-04-05 | Christopher Reed Williams | Method and apparatus for estimating the velocity vector of multiple vehicles on non-level and curved roads using a single camera |
US20110196569A1 (en) * | 2010-02-08 | 2011-08-11 | Hon Hai Precision Industry Co., Ltd. | Collision avoidance system and method |
US20120002052A1 (en) * | 2010-03-02 | 2012-01-05 | Panasonic Corporation | Obstacle detection apparatus, obstacle detection system having same, and obstacle detection method |
US20120148092A1 (en) * | 2010-12-09 | 2012-06-14 | Gorilla Technology Inc. | Automatic traffic violation detection system and method of the same |
US20120219183A1 (en) * | 2011-02-24 | 2012-08-30 | Daishi Mori | 3D Object Detecting Apparatus and 3D Object Detecting Method |
US20120226423A1 (en) * | 2011-03-03 | 2012-09-06 | Fuji Jukogyo Kabushiki Kaisha | Vehicle driving support apparatus |
US20120232733A1 (en) * | 2009-06-30 | 2012-09-13 | Valeo Vision | Method for determining, in a predictive manner, types of road situations for a vehicle |
US20120268602A1 (en) * | 2009-12-25 | 2012-10-25 | Hideaki Hirai | Object identifying apparatus, moving body control apparatus, and information providing apparatus |
US20130033600A1 (en) * | 2011-08-01 | 2013-02-07 | Hitachi, Ltd. | Image Processing Device |
US20130070091A1 (en) * | 2011-09-19 | 2013-03-21 | Michael Mojaver | Super resolution imaging and tracking system |
US20130084008A1 (en) * | 2010-06-12 | 2013-04-04 | Cambridge Enterprise Limited | Methods and systems for semantic label propagation |
US20130088596A1 (en) * | 2010-03-05 | 2013-04-11 | Panasonic Corporation | Monitoring system, method for controlling the same, and semiconductor integrated circuit for the same |
US20130151058A1 (en) * | 2011-12-09 | 2013-06-13 | GM Global Technology Operations LLC | Method and system for controlling a host vehicle |
US20130231829A1 (en) * | 2010-10-12 | 2013-09-05 | Volvo Lastvagnar Ab | Method and arrangement for entering a preceding vehicle autonomous following mode |
US20130304513A1 (en) * | 2012-05-08 | 2013-11-14 | Elwha Llc | Systems and methods for insurance based on monitored characteristics of an autonomous drive mode selection system |
US20130343613A1 (en) * | 2010-12-08 | 2013-12-26 | Thomas Heger | Camera-based method for determining distance in the case of a vehicle at standstill |
US20140168440A1 (en) * | 2011-09-12 | 2014-06-19 | Nissan Motor Co., Ltd. | Three-dimensional object detection device |
US20150008294A1 (en) * | 2011-06-09 | 2015-01-08 | J.M.R. Phi | Device for measuring speed and position of a vehicle moving along a guidance track, method and computer program product corresponding thereto |
US20150169992A1 (en) * | 2012-03-30 | 2015-06-18 | Google Inc. | Image similarity determination |
US9315178B1 (en) * | 2012-04-13 | 2016-04-19 | Google Inc. | Model checking for autonomous vehicles |
Family Cites Families (56)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2807608B2 (en) * | 1992-12-29 | 1998-10-08 | 株式会社ナムコ | Sorting processing apparatus, image synthesizing apparatus using the same, and sorting processing method |
JPH09507930A (en) * | 1993-12-08 | 1997-08-12 | ミネソタ マイニング アンド マニュファクチャリング カンパニー | Method and apparatus for background determination and subtraction for a single-lens vision system |
US5654890A (en) | 1994-05-31 | 1997-08-05 | Lockheed Martin | High resolution autonomous precision approach and landing system |
US5642093A (en) * | 1995-01-27 | 1997-06-24 | Fuji Jukogyo Kabushiki Kaisha | Warning system for vehicle |
US6661838B2 (en) * | 1995-05-26 | 2003-12-09 | Canon Kabushiki Kaisha | Image processing apparatus for detecting changes of an image signal and image processing method therefor |
US6335985B1 (en) * | 1998-01-07 | 2002-01-01 | Kabushiki Kaisha Toshiba | Object extraction apparatus |
US7136525B1 (en) | 1999-09-20 | 2006-11-14 | Microsoft Corporation | System and method for background maintenance of an image sequence |
US7082209B2 (en) * | 2000-08-31 | 2006-07-25 | Hitachi Kokusai Electric, Inc. | Object detecting method and object detecting apparatus and intruding object monitoring apparatus employing the object detecting method |
US6281806B1 (en) | 2000-10-12 | 2001-08-28 | Ford Global Technologies, Inc. | Driver road hazard warning and illumination system |
US20020130953A1 (en) * | 2001-03-13 | 2002-09-19 | John Riconda | Enhanced display of environmental navigation features to vehicle operator |
US20030058237A1 (en) * | 2001-09-27 | 2003-03-27 | Koninklijke Philips Electronics N.V. | Multi-layered background models for improved background-foreground segmentation |
US7266220B2 (en) * | 2002-05-09 | 2007-09-04 | Matsushita Electric Industrial Co., Ltd. | Monitoring device, monitoring method and program for monitoring |
US7190809B2 (en) * | 2002-06-28 | 2007-03-13 | Koninklijke Philips Electronics N.V. | Enhanced background model employing object classification for improved background-foreground segmentation |
JP4374211B2 (en) * | 2002-08-27 | 2009-12-02 | クラリオン株式会社 | Lane marker position detection method, lane marker position detection device, and lane departure warning device |
JP3868876B2 (en) * | 2002-09-25 | 2007-01-17 | 株式会社東芝 | Obstacle detection apparatus and method |
US7336803B2 (en) * | 2002-10-17 | 2008-02-26 | Siemens Corporate Research, Inc. | Method for scene modeling and change detection |
WO2004081854A1 (en) * | 2003-03-06 | 2004-09-23 | Animetrics, Inc. | Viewpoint-invariant detection and identification of a three-dimensional object from two-dimensional imagery |
DE10323915A1 (en) | 2003-05-23 | 2005-02-03 | Daimlerchrysler Ag | Camera-based position detection for a road vehicle |
JP4406381B2 (en) * | 2004-07-13 | 2010-01-27 | 株式会社東芝 | Obstacle detection apparatus and method |
US20060111841A1 (en) * | 2004-11-19 | 2006-05-25 | Jiun-Yuan Tseng | Method and apparatus for obstacle avoidance with camera vision |
JP4130435B2 (en) * | 2004-11-30 | 2008-08-06 | 本田技研工業株式会社 | Abnormality detection device for imaging device |
JP4130434B2 (en) * | 2004-11-30 | 2008-08-06 | 本田技研工業株式会社 | Abnormality detection device for imaging device |
US7639841B2 (en) * | 2004-12-20 | 2009-12-29 | Siemens Corporation | System and method for on-road detection of a vehicle using knowledge fusion |
JP4451315B2 (en) * | 2005-01-06 | 2010-04-14 | 富士重工業株式会社 | Vehicle driving support device |
US7130745B2 (en) * | 2005-02-10 | 2006-10-31 | Toyota Technical Center Usa, Inc. | Vehicle collision warning system |
US7720282B2 (en) * | 2005-08-02 | 2010-05-18 | Microsoft Corporation | Stereo image segmentation |
JP4752486B2 (en) * | 2005-12-15 | 2011-08-17 | 株式会社日立製作所 | Imaging device, video signal selection device, driving support device, automobile |
EP2296104A1 (en) * | 2006-01-10 | 2011-03-16 | Panasonic Corporation | Dynamic camera color correction device, and video search device using the same |
GB2437137A (en) | 2006-04-03 | 2007-10-17 | Autoliv Development Ab | Drivers aid that sensors the surrounding of the vehicle, and with a positioning system compares the detected objects to predict the driving conditions |
US7724962B2 (en) * | 2006-07-07 | 2010-05-25 | Siemens Corporation | Context adaptive approach in vehicle detection under various visibility conditions |
CN101187985B (en) * | 2006-11-17 | 2012-02-01 | 东软集团股份有限公司 | Method and device for classification boundary of identifying object classifier |
JP5132164B2 (en) * | 2007-02-22 | 2013-01-30 | 富士通株式会社 | Background image creation device |
ATE537662T1 (en) * | 2007-04-27 | 2011-12-15 | Honda Motor Co Ltd | SYSTEM, PROGRAM AND METHOD FOR VEHICLE PERIPHERAL MONITORING |
US8300887B2 (en) * | 2007-05-10 | 2012-10-30 | Honda Motor Co., Ltd. | Object detection apparatus, object detection method and object detection program |
US8644600B2 (en) * | 2007-06-05 | 2014-02-04 | Microsoft Corporation | Learning object cutout from a single example |
JP4967937B2 (en) * | 2007-09-06 | 2012-07-04 | 日本電気株式会社 | Image processing apparatus, method, and program |
JP4462316B2 (en) * | 2007-09-26 | 2010-05-12 | 株式会社デンソー | Route search device |
JP4650468B2 (en) * | 2007-09-26 | 2011-03-16 | 株式会社デンソー | Route search device |
TWI348659B (en) * | 2007-10-29 | 2011-09-11 | Ind Tech Res Inst | Method and system for object detection and tracking |
KR100951890B1 (en) * | 2008-01-25 | 2010-04-12 | 성균관대학교산학협력단 | Method for simultaneous recognition and pose estimation of object using in-situ monitoring |
US8379989B2 (en) * | 2008-04-01 | 2013-02-19 | Toyota Jidosha Kabushiki Kaisha | Image search apparatus and image processing apparatus |
US8005264B2 (en) * | 2008-06-09 | 2011-08-23 | Arcsoft, Inc. | Method of automatically detecting and tracking successive frames in a region of interesting by an electronic imaging device |
JP4513909B2 (en) * | 2008-07-07 | 2010-07-28 | 株式会社デンソー | Vehicle travel support device |
US8055445B2 (en) * | 2008-09-24 | 2011-11-08 | Delphi Technologies, Inc. | Probabilistic lane assignment method |
JP5221765B2 (en) | 2008-10-01 | 2013-06-26 | ハイ キー リミテッド | Image capturing apparatus calibration method and calibration system |
US8218818B2 (en) * | 2009-09-01 | 2012-07-10 | Behavioral Recognition Systems, Inc. | Foreground object tracking |
TWI413024B (en) * | 2009-11-19 | 2013-10-21 | Ind Tech Res Inst | Method and system for object detection |
JP2011210139A (en) * | 2010-03-30 | 2011-10-20 | Sony Corp | Image processing apparatus and method, and program |
US9165468B2 (en) | 2010-04-12 | 2015-10-20 | Robert Bosch Gmbh | Video based intelligent vehicle control system |
US8488881B2 (en) * | 2010-07-27 | 2013-07-16 | International Business Machines Corporation | Object segmentation at a self-checkout |
JP5704863B2 (en) * | 2010-08-26 | 2015-04-22 | キヤノン株式会社 | Image processing apparatus, image processing method, and storage medium |
US8599255B2 (en) * | 2010-12-07 | 2013-12-03 | Qnap Systems, Inc. | Video surveillance system based on Gaussian mixture modeling with two-type learning rate control scheme |
JP5637383B2 (en) | 2010-12-15 | 2014-12-10 | ソニー株式会社 | Image processing apparatus, image processing method, and program |
JP2012155612A (en) | 2011-01-27 | 2012-08-16 | Denso Corp | Lane detection apparatus |
JP5716464B2 (en) | 2011-03-07 | 2015-05-13 | 富士通株式会社 | Image processing program, image processing method, and image processing apparatus |
US20130027550A1 (en) * | 2011-07-29 | 2013-01-31 | Technische Universitat Berlin | Method and device for video surveillance |
-
2016
- 2016-04-04 US US15/090,089 patent/US10678259B1/en active Active
-
2020
- 2020-06-08 US US16/896,203 patent/US11079768B2/en active Active
-
2021
- 2021-08-02 US US17/391,778 patent/US20210356970A1/en active Pending
Patent Citations (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5847755A (en) * | 1995-01-17 | 1998-12-08 | Sarnoff Corporation | Method and apparatus for detecting object movement within an image sequence |
US6151539A (en) * | 1997-11-03 | 2000-11-21 | Volkswagen Ag | Autonomous vehicle arrangement and method for controlling an autonomous vehicle |
US20040090117A1 (en) * | 2000-07-26 | 2004-05-13 | Ingo Dudeck | Automatic brake and steering system and method for a vehicle |
US7327855B1 (en) * | 2001-06-20 | 2008-02-05 | Hrl Laboratories, Llc | Vision-based highway overhead structure detection system |
US20040126014A1 (en) * | 2002-12-31 | 2004-07-01 | Lipton Alan J. | Video scene background maintenance using statistical pixel modeling |
US20040151342A1 (en) * | 2003-01-30 | 2004-08-05 | Venetianer Peter L. | Video scene background maintenance using change detection and classification |
US20050165550A1 (en) * | 2004-01-23 | 2005-07-28 | Ryuzo Okada | Obstacle detection apparatus and a method therefor |
US20050278088A1 (en) * | 2004-05-29 | 2005-12-15 | Craig Thorner | Method and apparatus for collision avoidance and enhanced visibility in vehicles |
US7920959B1 (en) * | 2005-05-01 | 2011-04-05 | Christopher Reed Williams | Method and apparatus for estimating the velocity vector of multiple vehicles on non-level and curved roads using a single camera |
US20090135065A1 (en) * | 2006-02-24 | 2009-05-28 | Toyota Jidosha Kabushiki Kaisha | Object Detecting Apparatus and Method for Detecting an Object |
US20080059007A1 (en) * | 2006-06-09 | 2008-03-06 | Whittaker William L | System and method for autonomously convoying vehicles |
US20080239078A1 (en) * | 2006-11-21 | 2008-10-02 | Harman Becker Automotive Systems Gmbh | Video image presentation system |
US20100110193A1 (en) * | 2007-01-12 | 2010-05-06 | Sachio Kobayashi | Lane recognition device, vehicle, lane recognition method, and lane recognition program |
US20090028388A1 (en) * | 2007-07-24 | 2009-01-29 | Nec Electronics Corporation | On-vehicle image processing apparatus |
US20090140887A1 (en) * | 2007-11-29 | 2009-06-04 | Breed David S | Mapping Techniques Using Probe Vehicles |
US20100034423A1 (en) * | 2008-08-06 | 2010-02-11 | Tao Zhao | System and method for detecting and tracking an object of interest in spatio-temporal space |
US20100165102A1 (en) * | 2008-12-30 | 2010-07-01 | Hella Kgaa Hueck & Co. | Method and device for determining a change in the pitch angle of a camera of a vehicle |
US20120232733A1 (en) * | 2009-06-30 | 2012-09-13 | Valeo Vision | Method for determining, in a predictive manner, types of road situations for a vehicle |
US20120268602A1 (en) * | 2009-12-25 | 2012-10-25 | Hideaki Hirai | Object identifying apparatus, moving body control apparatus, and information providing apparatus |
US20110196569A1 (en) * | 2010-02-08 | 2011-08-11 | Hon Hai Precision Industry Co., Ltd. | Collision avoidance system and method |
US20120002052A1 (en) * | 2010-03-02 | 2012-01-05 | Panasonic Corporation | Obstacle detection apparatus, obstacle detection system having same, and obstacle detection method |
US20130088596A1 (en) * | 2010-03-05 | 2013-04-11 | Panasonic Corporation | Monitoring system, method for controlling the same, and semiconductor integrated circuit for the same |
US20130084008A1 (en) * | 2010-06-12 | 2013-04-04 | Cambridge Enterprise Limited | Methods and systems for semantic label propagation |
US20130231829A1 (en) * | 2010-10-12 | 2013-09-05 | Volvo Lastvagnar Ab | Method and arrangement for entering a preceding vehicle autonomous following mode |
US20130343613A1 (en) * | 2010-12-08 | 2013-12-26 | Thomas Heger | Camera-based method for determining distance in the case of a vehicle at standstill |
US20120148092A1 (en) * | 2010-12-09 | 2012-06-14 | Gorilla Technology Inc. | Automatic traffic violation detection system and method of the same |
US20120219183A1 (en) * | 2011-02-24 | 2012-08-30 | Daishi Mori | 3D Object Detecting Apparatus and 3D Object Detecting Method |
US20120226423A1 (en) * | 2011-03-03 | 2012-09-06 | Fuji Jukogyo Kabushiki Kaisha | Vehicle driving support apparatus |
US20150008294A1 (en) * | 2011-06-09 | 2015-01-08 | J.M.R. Phi | Device for measuring speed and position of a vehicle moving along a guidance track, method and computer program product corresponding thereto |
US20130033600A1 (en) * | 2011-08-01 | 2013-02-07 | Hitachi, Ltd. | Image Processing Device |
US20140168440A1 (en) * | 2011-09-12 | 2014-06-19 | Nissan Motor Co., Ltd. | Three-dimensional object detection device |
US20130070091A1 (en) * | 2011-09-19 | 2013-03-21 | Michael Mojaver | Super resolution imaging and tracking system |
US20130151058A1 (en) * | 2011-12-09 | 2013-06-13 | GM Global Technology Operations LLC | Method and system for controlling a host vehicle |
US20150169992A1 (en) * | 2012-03-30 | 2015-06-18 | Google Inc. | Image similarity determination |
US9315178B1 (en) * | 2012-04-13 | 2016-04-19 | Google Inc. | Model checking for autonomous vehicles |
US20130304513A1 (en) * | 2012-05-08 | 2013-11-14 | Elwha Llc | Systems and methods for insurance based on monitored characteristics of an autonomous drive mode selection system |
Non-Patent Citations (1)
Title |
---|
Kyutoku et al. "On-Road Obstacle Detection by Comparing Present and Past In-Vehicle Camera Images" MVA2011 IAPR Conference on Machine Vision Applications, June 13-15, 2011, Nara Japan, pp. 357-360 * |
Also Published As
Publication number | Publication date |
---|---|
US10678259B1 (en) | 2020-06-09 |
US20200301440A1 (en) | 2020-09-24 |
US11079768B2 (en) | 2021-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11181914B2 (en) | Use of detected objects for image processing | |
US11731629B2 (en) | Robust method for detecting traffic signals and their associated states | |
US11079768B2 (en) | Use of a reference image to detect a road obstacle | |
US9561797B2 (en) | Predictive reasoning for controlling speed of a vehicle | |
US9063548B1 (en) | Use of previous detections for lane marker detection | |
US9052721B1 (en) | Method for correcting alignment of vehicle mounted laser scans with an elevation map for obstacle detection | |
US9207680B1 (en) | Estimating multi-vehicle motion characteristics by finding stable reference points | |
US8989944B1 (en) | Methods and devices for determining movements of an object in an environment | |
US9607226B2 (en) | Methods and systems for object detection using multiple sensors | |
US8781670B2 (en) | Controlling vehicle lateral lane positioning | |
EP2958783B1 (en) | A method to detect nearby aggressive drivers and adjust driving modes | |
US9097804B1 (en) | Object and ground segmentation from a sparse one-dimensional range data | |
US9026300B2 (en) | Methods and systems to aid autonomous vehicles driving through a lane merge | |
EP3617018B1 (en) | Actively modifying a field of view of an autonomous vehicle in view of constraints | |
US8504233B1 (en) | Safely navigating on roads through maintaining safe distance from other vehicles | |
EP2937815A2 (en) | Methods and systems for object detection using laser point clouds | |
US9766628B1 (en) | Vision-based object detection using a polar grid |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: WAYMO HOLDING INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:GOOGLE INC.;REEL/FRAME:057153/0785 Effective date: 20170321 Owner name: WAYMO LLC, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:WAYMO HOLDING INC.;REEL/FRAME:057066/0918 Effective date: 20170322 Owner name: GOOGLE INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:FERGUSON, DAVID IAN;ZHU, JIAJUN;REEL/FRAME:057065/0805 Effective date: 20120912 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |