CN113822234A - Target detection early warning analysis method, system and terminal based on vehicle-mounted thermal imaging - Google Patents
Target detection early warning analysis method, system and terminal based on vehicle-mounted thermal imaging Download PDFInfo
- Publication number
- CN113822234A CN113822234A CN202111381644.6A CN202111381644A CN113822234A CN 113822234 A CN113822234 A CN 113822234A CN 202111381644 A CN202111381644 A CN 202111381644A CN 113822234 A CN113822234 A CN 113822234A
- Authority
- CN
- China
- Prior art keywords
- image
- motion
- target object
- vehicle
- target
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30196—Human being; Person
-
- 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
Abstract
The invention discloses a target detection early warning analysis method, a system and a terminal based on vehicle-mounted thermal imaging, relating to the technical field of vehicle-mounted thermal imaging detection, and the technical scheme is as follows: extracting two thermal imaging images as a first image and a second image; determining a motion straight-line track of a target object; identifying and extracting temperature distribution information of the joint part and the muscle part, and respectively determining the facing directions of the target object in the first image and the second image; analyzing the temperature distribution difference to obtain the motion amount change value of the target object, and performing simulation analysis to obtain the motion prediction track and the uniform acceleration absolute value of the target object; and determining the motion range of the target object, and performing dynamic early warning after simulating and analyzing the accident probability of the collision between the target object and the target vehicle. The method can obtain the motion situation of the accurately represented target object within the preset interval time, so that the motion trail of the simulated target object is more consistent with the actual situation; the false alarm rate is reduced, and the situation that the driver is in a high-concentration state of attention for a long time is avoided.
Description
Technical Field
The invention relates to the technical field of vehicle-mounted thermal imaging detection, in particular to a target detection early warning analysis method, a target detection early warning analysis system and a target detection early warning analysis terminal based on vehicle-mounted thermal imaging.
Background
The infrared thermal imaging technology is that according to the detected radiation energy of the object, the radiation energy is converted into a thermal image of the target object through system processing, and the thermal image is displayed in gray scale or pseudo color, so that the temperature distribution of the detected target is obtained, and the state of the object is judged. Compared with the image recognition technology, the infrared imaging technology adopts the characteristics of non-contact detection, capability of working at night and the like, and is widely applied to the fields of fire prevention monitoring, inspection and quarantine, disease detection, vehicle auxiliary driving and the like.
At present, infrared thermal imaging applied in vehicle auxiliary driving mainly judges the specific influence condition of a target object on normal driving of a target vehicle through detected information such as the temperature distribution shape of the target object, the relative position of the target object relative to the target vehicle, the driving speed of the target vehicle and the like, can warn a driver in time, and is convenient for the driver to make emergency preparation in advance; in addition, environmental monitoring data can be provided for unmanned driving, and basic data is provided for safe and stable unmanned driving.
However, infrared thermal imaging applied in vehicle-assisted driving does not take the motion posture of a target into consideration when detecting the target; on one hand, if the target object is in a high-speed moving state, even if the distance is long, the influence on the normal driving of the vehicle can still be caused; on the other hand, if the target object is in a low-speed motion state or a static state, normal driving of the vehicle is not affected generally even if the target object is close to the target object, so that the conventional vehicle auxiliary driving based on infrared thermal imaging target detection has a high false alarm rate, accidents are easily caused to a certain extent, and meanwhile, a driver is easily caused to enter an exhausted state quickly due to being in a high-concentration state for a long time. Therefore, how to research and design a target detection and early warning analysis method, system and terminal based on vehicle-mounted thermal imaging, which can overcome the defects, is a problem which is urgently needed to be solved at present.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a target detection early warning analysis method, a target detection early warning analysis system and a target detection early warning analysis terminal based on vehicle-mounted thermal imaging.
The technical purpose of the invention is realized by the following technical scheme:
in a first aspect, a target detection and early warning analysis method based on vehicle-mounted thermal imaging is provided, which comprises the following steps:
extracting two thermal imaging images from a thermal imaging video stream at preset intervals as a first image and a second image;
determining a motion linear track of the target object within a preset interval time according to the running speed of the target vehicle, the position conditions of the target object in the first image and the second image and the temperature compensation parameter of the distance in thermal imaging;
identifying and extracting temperature distribution information of joint parts and muscle parts in the first image and the second image, respectively determining facing directions of the target object in the first image and the second image according to the temperature distribution information, and taking the facing directions as motion directions of corresponding moments;
analyzing the temperature distribution difference of corresponding joint parts and muscle parts in the first image and the second image under the condition of the same area to obtain the motion amount change value of the target object in the preset interval time, and performing simulation analysis by combining the motion linear track, the motion direction, the preset interval time and the motion amount change value to obtain the motion prediction track and the uniform acceleration absolute value of the target object;
and determining the movement range of the target object according to the preset deflection angle and the movement direction at the current moment, simulating and analyzing the accident probability of direct collision between the target object and the target vehicle, and performing dynamic early warning after matching the corresponding danger level according to the accident probability.
Furthermore, the first image and the second image respectively comprise a front side partial image, a rear side partial image, a left side partial image and a right side partial image, and the collection visual angle range of each partial image is a 90-degree included angle range of the corresponding side.
Further, the process of determining the motion straight line trajectory specifically includes:
acquiring a first temperature compensation value of a first image and a second temperature compensation value of a second image generated by a thermal imaging detector, and determining a first distance between a target object and a target vehicle in the first image and a second distance between the target object and the target vehicle in the second image;
determining the running displacement of the target vehicle according to the running speed of the target vehicle, converting the running displacement into the image displacement of the target object relative to the target vehicle in the thermal imaging image, and determining the relative position of the target object in the second image according to the image displacement;
and determining the motion straight line track of the target object according to the connecting line between the actual position and the relative position of the target object in the second image.
Further, the process of determining the facing direction of the target object specifically includes:
determining the main body shape of the target object including the main trunk and the limbs according to the distribution shape and the distribution relative position corresponding to the joint part and the muscle parts corresponding to the two sides;
correcting the main body form according to the body coordination characteristics of the human body movement to obtain a final form;
and determining the facing direction representing the movement of the predicted target object according to the change trends of the face front-looking direction, the trunk twisting direction and the limb swinging direction in the final form.
Further, the obtaining process of the motion amount change value specifically includes:
intercepting a preset area region from the coverage range of the joint part or the muscle part, and calculating by a calculus method to obtain a temperature superposition value of the preset area region;
respectively summing the temperature superposition values corresponding to the joint part and the muscle part which are simultaneously visible in the first image and the second image to obtain the total temperature value of the first image and the second image;
and calculating to obtain the temperature variation according to the difference between the total temperature values of the first image and the second image, and converting the temperature variation into the motion quantity variation according to a preset variation coefficient.
Furthermore, when the first image and the second image are subjected to temperature distribution difference analysis, the temperature data in the first image and the second image are converted into temperature data under the same distance condition according to the ratio of temperature compensation parameters of the distance in the first image and the distance in the second image.
Further, the simulation analysis process of the motion prediction trajectory and the absolute value of the uniform acceleration specifically includes:
calculating to obtain a unit time change value according to the ratio of the motion amount change value to the preset interval time, and taking a historical acceleration absolute value and an average speed matched with the unit time change value as a current uniform acceleration absolute value;
and fitting on the motion straight line track according to the average speed, the absolute value of the uniform acceleration, the preset interval time and the motion direction of the start and stop of the target object to obtain a motion prediction track.
Further, the simulation analysis process of the accident probability specifically includes:
deflecting the left side by a preset deflection angle C and deflecting the right side by the preset deflection angle C in the motion direction to obtain a motion range < -C, C >;
predicting a motion path of the analysis target object in a preset period according to the motion prediction track, rotating the motion path by a sudden change angle k by taking the current position as a center, analyzing whether the rotated motion path collides with a target vehicle or not,
；
and (4) counting the ratio of the range of the rotating motion path corresponding to the mutation angle k and the target vehicle to the motion range to obtain the accident probability.
In a second aspect, a target detection and early warning analysis method system based on vehicle-mounted thermal imaging is provided, which includes:
the image extraction module is used for extracting two thermal imaging images from the thermal imaging video stream at preset interval time as a first image and a second image;
the track determining module is used for determining a motion straight-line track of the target object within preset interval time according to the running speed of the target vehicle, the position conditions of the target object in the first image and the second image and the temperature compensation parameter of the distance in thermal imaging;
the direction identification module is used for identifying and extracting temperature distribution information of joint parts and muscle parts in the first image and the second image, respectively determining facing directions of target objects in the first image and the second image according to the temperature distribution information, and taking the facing directions as motion directions of corresponding moments;
the simulation analysis module is used for obtaining the motion amount change value of the target object in the preset interval time according to the temperature distribution difference analysis of the corresponding joint part and muscle part in the first image and the second image under the condition of the same area, and obtaining the motion prediction track and the uniform acceleration absolute value of the target object by combining the motion linear track, the motion direction, the preset interval time and the motion amount change value simulation analysis;
and the probability early warning module is used for determining the motion range of the target object according to the preset deflection angle and the motion direction at the current moment, simulating and analyzing the accident probability of direct collision between the target object and the target vehicle, and performing dynamic early warning after matching the corresponding danger level according to the accident probability.
In a third aspect, a computer terminal is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the method for detecting and analyzing an early warning of an object based on vehicle-mounted thermal imaging according to any one of the first aspect is implemented.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the target detection early warning analysis method based on vehicle-mounted thermal imaging, the first image and the second image are collected at the preset interval time, the movement directions and positions of the two images and the temperature distribution difference of the joint part and the muscle part are analyzed, and the movement situation of a target object in the preset interval time can be accurately represented by combining historical data, so that the movement track of the simulated target object is more consistent with the actual situation; meanwhile, the deflection condition corresponding to the emergency is considered, the danger early warning of the target object can be continuously updated along with the driving, namely the false alarm rate is reduced, the driver is prevented from being in a high-concentration state of attention for a long time, and reliable reference information is provided for the auxiliary driving of the vehicle;
2. the invention carries out matching analysis on the distribution conditions of the joint part and the muscle part of the target object, can accurately match specific forms for the target object, and carries out correction processing on the forms obtained by matching according to the body coordination characteristics of human motion, so that the accuracy of determining the direction of the motion of the target object is high;
3. according to the invention, the temperature differences of the joint part and the muscle part which can be visually displayed in the first image and the second image are superposed and summed, and the temperature variation is converted into the motion amount variation value according to the preset variation coefficient, so that the absolute value and the average rate of the uniform acceleration can be conveniently determined subsequently; in addition, the influence of the temperature compensation parameter difference of the distance on the temperature is also considered, so that the error of the calculation result of the motion quantity change value is small.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a flow chart in an embodiment of the invention;
FIG. 2 is a schematic diagram illustrating the analysis of the linear trajectory of the target object according to the embodiment of the present invention;
FIG. 3 is a schematic diagram of an analysis of the probability of an incident according to an embodiment of the present invention;
fig. 4 is a block diagram of a system in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1: a target detection early warning analysis method based on vehicle-mounted thermal imaging is shown in figure 1 and comprises the following steps:
s1: extracting two thermal imaging images from a thermal imaging video stream at preset intervals as a first image and a second image;
s2: determining a motion linear track of the target object within a preset interval time according to the running speed of the target vehicle, the position conditions of the target object in the first image and the second image and the temperature compensation parameter of the distance in thermal imaging;
s3: identifying and extracting temperature distribution information of joint parts and muscle parts in the first image and the second image, respectively determining facing directions of the target object in the first image and the second image according to the temperature distribution information, and taking the facing directions as motion directions of corresponding moments;
s4: analyzing the temperature distribution difference of corresponding joint parts and muscle parts in the first image and the second image under the condition of the same area to obtain the motion amount change value of the target object in the preset interval time, and performing simulation analysis by combining the motion linear track, the motion direction, the preset interval time and the motion amount change value to obtain the motion prediction track and the uniform acceleration absolute value of the target object;
s5: and determining the movement range of the target object according to the preset deflection angle and the movement direction at the current moment, simulating and analyzing the accident probability of direct collision between the target object and the target vehicle, and performing dynamic early warning after matching the corresponding danger level according to the accident probability.
In this embodiment, the first image and the second image each include a front partial image, a rear partial image, a left partial image, and a right partial image, and the collection view angle range of each partial image is a 90-degree included angle range of the corresponding side. In addition, in order to improve the comprehensiveness of target detection coverage, thermal imaging image acquisition can be performed through 6 or 8 infrared detectors. 6 infrared detectors to: one in front and back, and two in left and right. 8 infrared detectors to: one for each of front, back, left and right, and one for each of left front, right front, left back and right back.
As shown in fig. 2, the process of determining the motion straight line trajectory specifically includes: acquiring a first temperature compensation value of a first image and a second temperature compensation value of a second image generated by a thermal imaging detector, and determining a first distance between a target object and a target vehicle in the first image and a second distance between the target object and the target vehicle in the second image; determining the running displacement of the target vehicle according to the running speed of the target vehicle, converting the running displacement into the image displacement of the target object relative to the target vehicle in the thermal imaging image, and determining the relative position of the target object in the second image according to the image displacement; and determining the motion straight line track of the target object according to the connecting line between the actual position and the relative position of the target object in the second image.
For example, assume that the initial position of the target object is a, the position after the preset interval time is d, and the target vehicle is o. The first image selects a left partial image acquired for the area A, and the second image selects a left partial image acquired for the area A and a front partial image acquired for the area B. Where X is the travel displacement, α is the image displacement, and X + α = 0. The relative position of the target object in the second image is b, and the finally determined motion straight-line track is beta.
The facing direction determining process of the target object specifically comprises the following steps: determining the main body shape of the target object including the main trunk and the limbs according to the distribution shape and the distribution relative position corresponding to the joint part and the muscle parts corresponding to the two sides; correcting the main body form according to the body coordination characteristics of the human body movement to obtain a final form; and determining the facing direction representing the movement of the predicted target object according to the change trends of the face front-looking direction, the trunk twisting direction and the limb swinging direction in the final form.
The process of obtaining the motion quantity change value is as follows: intercepting a preset area region from the coverage range of the joint part or the muscle part, and calculating by a calculus method to obtain a temperature superposition value of the preset area region; respectively summing the temperature superposition values corresponding to the joint part and the muscle part which are simultaneously visible in the first image and the second image to obtain the total temperature value of the first image and the second image; and calculating to obtain the temperature variation according to the difference between the total temperature values of the first image and the second image, and converting the temperature variation into the motion quantity variation according to a preset variation coefficient.
In addition, when the first image and the second image are subjected to temperature distribution difference analysis, the temperature data in the first image and the second image are converted into temperature data under the same distance condition according to the ratio of the temperature compensation parameters of the distance in the first image and the distance in the second image.
The simulation analysis process of the motion prediction track and the uniform acceleration absolute value specifically comprises the following steps: calculating to obtain a unit time change value according to the ratio of the motion amount change value to the preset interval time, and taking a historical acceleration absolute value and an average speed matched with the unit time change value as a current uniform acceleration absolute value; and fitting on the motion straight line track according to the average speed, the absolute value of the uniform acceleration, the preset interval time and the motion direction of the start and stop of the target object to obtain a motion prediction track.
As shown in fig. 3, the determined motion direction of the first image is m, the determined motion direction of the second image is n, the predicted motion trajectory is z, and the predicted motion path is assumed to coincide with the motion direction n. The simulation analysis process of the accident probability specifically comprises the following steps: deflecting left and right by preset deflection angles C in the motion direction to obtain motion ranges of [ -C, C]And further n is in the direction 0; predicting a motion path of the analysis target object in a preset period according to the motion prediction track, rotating the motion path by a sudden change angle k by taking the current position as a center, analyzing whether the rotated motion path collides with a target vehicle or not,
(ii) a And (4) counting the ratio of the range of the rotating motion path corresponding to the mutation angle k and the target vehicle to the motion range to obtain the accident probability.
Example 2: a target detection early warning analysis method system based on vehicle-mounted thermal imaging is shown in FIG. 4 and comprises an image extraction module, a track determination module, a direction identification module, a simulation analysis module and a probability early warning module.
The image extraction module is used for extracting two thermal imaging images from a thermal imaging video stream at preset interval time as a first image and a second image; the track determining module is used for determining a motion straight-line track of the target object within preset interval time according to the running speed of the target vehicle, the position conditions of the target object in the first image and the second image and the temperature compensation parameter of the distance in thermal imaging; the direction identification module is used for identifying and extracting temperature distribution information of joint parts and muscle parts in the first image and the second image, respectively determining facing directions of target objects in the first image and the second image according to the temperature distribution information, and taking the facing directions as motion directions of corresponding moments; the simulation analysis module is used for obtaining the motion amount change value of the target object in the preset interval time according to the temperature distribution difference analysis of the corresponding joint part and muscle part in the first image and the second image under the condition of the same area, and obtaining the motion prediction track and the uniform acceleration absolute value of the target object by combining the motion linear track, the motion direction, the preset interval time and the motion amount change value simulation analysis; and the probability early warning module is used for determining the motion range of the target object according to the preset deflection angle and the motion direction at the current moment, simulating and analyzing the accident probability of direct collision between the target object and the target vehicle, and performing dynamic early warning after matching the corresponding danger level according to the accident probability.
The working principle is as follows: according to the invention, the first image and the second image are acquired at preset interval time, the movement directions and positions of the two images and the temperature distribution difference of the joint part and the muscle part are analyzed, and the movement situation of the target object in the preset interval time can be accurately represented by combining historical data, so that the movement track of the simulated target object is more in line with the actual situation; meanwhile, the deflection condition corresponding to the emergency is considered, the danger early warning of the target object can be continuously updated along with the driving, namely the false alarm rate is reduced, the condition that a driver is in a high concentration state of attention for a long time is avoided, and reliable reference information is provided for the auxiliary driving of the vehicle.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. The target detection early warning analysis method based on vehicle-mounted thermal imaging is characterized by comprising the following steps of:
extracting two thermal imaging images from a thermal imaging video stream at preset intervals as a first image and a second image;
determining a motion linear track of the target object within a preset interval time according to the running speed of the target vehicle, the position conditions of the target object in the first image and the second image and the temperature compensation parameter of the distance in thermal imaging;
identifying and extracting temperature distribution information of joint parts and muscle parts in the first image and the second image, respectively determining facing directions of the target object in the first image and the second image according to the temperature distribution information, and taking the facing directions as motion directions of corresponding moments;
analyzing the temperature distribution difference of corresponding joint parts and muscle parts in the first image and the second image under the condition of the same area to obtain the motion amount change value of the target object in the preset interval time, and performing simulation analysis by combining the motion linear track, the motion direction, the preset interval time and the motion amount change value to obtain the motion prediction track and the uniform acceleration absolute value of the target object;
and determining the movement range of the target object according to the preset deflection angle and the movement direction at the current moment, simulating and analyzing the accident probability of direct collision between the target object and the target vehicle, and performing dynamic early warning after matching the corresponding danger level according to the accident probability.
2. The vehicle-mounted imaging-based target detection and early-warning analysis method according to claim 1, wherein the first image and the second image respectively comprise a front side partial image, a rear side partial image, a left side partial image and a right side partial image, and the acquisition visual angle range of each partial image is a 90-degree included angle range of the corresponding side.
3. The vehicle-mounted imaging-based target detection and early warning analysis method according to claim 1, wherein the determination process of the motion straight line trajectory specifically comprises the following steps:
acquiring a first temperature compensation value of a first image and a second temperature compensation value of a second image generated by a thermal imaging detector, and determining a first distance between a target object and a target vehicle in the first image and a second distance between the target object and the target vehicle in the second image;
determining the running displacement of the target vehicle according to the running speed of the target vehicle, converting the running displacement into the image displacement of the target object relative to the target vehicle in the thermal imaging image, and determining the relative position of the target object in the second image according to the image displacement;
and determining the motion straight line track of the target object according to the connecting line between the actual position and the relative position of the target object in the second image.
4. The vehicle-mounted imaging-based target detection and early warning analysis method according to claim 1, wherein the process of determining the facing direction of the target object specifically comprises the following steps:
determining the main body shape of the target object including the main trunk and the limbs according to the distribution shape and the distribution relative position corresponding to the joint part and the muscle parts corresponding to the two sides;
correcting the main body form according to the body coordination characteristics of the human body movement to obtain a final form;
and determining the facing direction representing the movement of the predicted target object according to the change trends of the face front-looking direction, the trunk twisting direction and the limb swinging direction in the final form.
5. The vehicle-mounted imaging-based target detection and early warning analysis method according to claim 1, wherein the motion amount change value is obtained by a process comprising:
intercepting a preset area region from the coverage range of the joint part or the muscle part, and calculating by a calculus method to obtain a temperature superposition value of the preset area region;
respectively summing the temperature superposition values corresponding to the joint part and the muscle part which are simultaneously visible in the first image and the second image to obtain the total temperature value of the first image and the second image;
and calculating to obtain the temperature variation according to the difference between the total temperature values of the first image and the second image, and converting the temperature variation into the motion quantity variation according to a preset variation coefficient.
6. The method as claimed in claim 5, wherein the temperature data in the first and second images are converted into temperature data at the same distance according to a ratio of temperature compensation parameters of the distance between the first and second images when the first and second images are subjected to temperature distribution difference analysis.
7. The vehicle-mounted imaging-based target detection and early warning analysis method according to claim 1, wherein the simulation analysis process of the motion prediction trajectory and the absolute value of the uniform acceleration specifically comprises the following steps:
calculating to obtain a unit time change value according to the ratio of the motion amount change value to the preset interval time, and taking a historical acceleration absolute value and an average speed matched with the unit time change value as a current uniform acceleration absolute value;
and fitting on the motion straight line track according to the average speed, the absolute value of the uniform acceleration, the preset interval time and the motion direction of the start and stop of the target object to obtain a motion prediction track.
8. The vehicle-mounted imaging-based target detection and early warning analysis method according to claim 1, wherein the simulation analysis process of the accident probability specifically comprises the following steps:
deflecting the left side by a preset deflection angle C and deflecting the right side by the preset deflection angle C in the motion direction to obtain a motion range < -C, C >;
predicting the motion path of the analysis target object in a preset period according to the motion prediction track, rotating the motion path by a sudden change angle k by taking the current position as the center, and analyzing whether the rotated motion path is in a preset state or notIn the event of a collision with a target vehicle,
；
and (4) counting the ratio of the range of the rotating motion path corresponding to the mutation angle k and the target vehicle to the motion range to obtain the accident probability.
9. A target detection early warning analysis method system based on vehicle-mounted thermal imaging is characterized by comprising the following steps:
the image extraction module is used for extracting two thermal imaging images from the thermal imaging video stream at preset interval time as a first image and a second image;
the track determining module is used for determining a motion straight-line track of the target object within preset interval time according to the running speed of the target vehicle, the position conditions of the target object in the first image and the second image and the temperature compensation parameter of the distance in thermal imaging;
the direction identification module is used for identifying and extracting temperature distribution information of joint parts and muscle parts in the first image and the second image, respectively determining facing directions of target objects in the first image and the second image according to the temperature distribution information, and taking the facing directions as motion directions of corresponding moments;
the simulation analysis module is used for obtaining the motion amount change value of the target object in the preset interval time according to the temperature distribution difference analysis of the corresponding joint part and muscle part in the first image and the second image under the condition of the same area, and obtaining the motion prediction track and the uniform acceleration absolute value of the target object by combining the motion linear track, the motion direction, the preset interval time and the motion amount change value simulation analysis;
and the probability early warning module is used for determining the motion range of the target object according to the preset deflection angle and the motion direction at the current moment, simulating and analyzing the accident probability of direct collision between the target object and the target vehicle, and performing dynamic early warning after matching the corresponding danger level according to the accident probability.
10. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for detecting and analyzing an early warning of an object based on thermal imaging according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111381644.6A CN113822234B (en) | 2021-11-22 | 2021-11-22 | Target detection early warning analysis method, system and terminal based on vehicle-mounted thermal imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111381644.6A CN113822234B (en) | 2021-11-22 | 2021-11-22 | Target detection early warning analysis method, system and terminal based on vehicle-mounted thermal imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113822234A true CN113822234A (en) | 2021-12-21 |
| CN113822234B CN113822234B (en) | 2022-04-22 |
Family
ID=78919420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111381644.6A Active CN113822234B (en) | 2021-11-22 | 2021-11-22 | Target detection early warning analysis method, system and terminal based on vehicle-mounted thermal imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822234B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685516A (en) * | 2011-03-07 | 2012-09-19 | 李慧盈 | Active safety type assistant driving method based on stereoscopic vision |
| CN104442571A (en) * | 2014-11-26 | 2015-03-25 | 重庆长安汽车股份有限公司 | Night vision navigation integration system and control method |
| CN105426852A (en) * | 2015-11-23 | 2016-03-23 | 天津津航技术物理研究所 | Method for identifying pedestrians by vehicle-mounted monocular long-wave infrared camera |
| CN109878407A (en) * | 2019-02-27 | 2019-06-14 | 中国第一汽车股份有限公司 | Nighttime driving pedestrian based on mobile Internet prompts auxiliary system and method |
| US20190258251A1 (en) * | 2017-11-10 | 2019-08-22 | Nvidia Corporation | Systems and methods for safe and reliable autonomous vehicles |
| CN110490116A (en) * | 2019-08-13 | 2019-11-22 | 广州三木智能科技有限公司 | A kind of far infrared pedestrian detection method of selective search and machine learning classification |
| US20190370568A1 (en) * | 2016-09-22 | 2019-12-05 | Denso Corporation | Object detection apparatus and object detection method |
| CN111907407A (en) * | 2020-07-20 | 2020-11-10 | 珠海市极太人工智能有限公司 | Early warning system for vehicle-mounted thermal imaging detection of targets with different danger levels |
| CN111914702A (en) * | 2020-07-20 | 2020-11-10 | 珠海市极太人工智能有限公司 | Scene self-adaptive system for improving vehicle-mounted infrared thermal imaging recognition accuracy |
| CN112106348A (en) * | 2018-05-11 | 2020-12-18 | 阿诺·查斯 | Passive infrared pedestrian detection and avoidance system |
| CN112242058A (en) * | 2020-05-29 | 2021-01-19 | 北京新能源汽车技术创新中心有限公司 | Target abnormity detection method and device based on traffic monitoring video and storage medium |
| CN112399144A (en) * | 2020-11-05 | 2021-02-23 | 上海明略人工智能(集团)有限公司 | Thermal imaging monitoring early warning method and device and thermal imaging monitoring management system |
| CN113298041A (en) * | 2021-06-21 | 2021-08-24 | 黑芝麻智能科技(上海)有限公司 | Method and system for calibrating driver distraction reference direction |
-
2021
- 2021-11-22 CN CN202111381644.6A patent/CN113822234B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685516A (en) * | 2011-03-07 | 2012-09-19 | 李慧盈 | Active safety type assistant driving method based on stereoscopic vision |
| CN104442571A (en) * | 2014-11-26 | 2015-03-25 | 重庆长安汽车股份有限公司 | Night vision navigation integration system and control method |
| CN105426852A (en) * | 2015-11-23 | 2016-03-23 | 天津津航技术物理研究所 | Method for identifying pedestrians by vehicle-mounted monocular long-wave infrared camera |
| US20190370568A1 (en) * | 2016-09-22 | 2019-12-05 | Denso Corporation | Object detection apparatus and object detection method |
| US20190258251A1 (en) * | 2017-11-10 | 2019-08-22 | Nvidia Corporation | Systems and methods for safe and reliable autonomous vehicles |
| CN112106348A (en) * | 2018-05-11 | 2020-12-18 | 阿诺·查斯 | Passive infrared pedestrian detection and avoidance system |
| CN109878407A (en) * | 2019-02-27 | 2019-06-14 | 中国第一汽车股份有限公司 | Nighttime driving pedestrian based on mobile Internet prompts auxiliary system and method |
| CN110490116A (en) * | 2019-08-13 | 2019-11-22 | 广州三木智能科技有限公司 | A kind of far infrared pedestrian detection method of selective search and machine learning classification |
| CN112242058A (en) * | 2020-05-29 | 2021-01-19 | 北京新能源汽车技术创新中心有限公司 | Target abnormity detection method and device based on traffic monitoring video and storage medium |
| CN111907407A (en) * | 2020-07-20 | 2020-11-10 | 珠海市极太人工智能有限公司 | Early warning system for vehicle-mounted thermal imaging detection of targets with different danger levels |
| CN111914702A (en) * | 2020-07-20 | 2020-11-10 | 珠海市极太人工智能有限公司 | Scene self-adaptive system for improving vehicle-mounted infrared thermal imaging recognition accuracy |
| CN112399144A (en) * | 2020-11-05 | 2021-02-23 | 上海明略人工智能(集团)有限公司 | Thermal imaging monitoring early warning method and device and thermal imaging monitoring management system |
| CN113298041A (en) * | 2021-06-21 | 2021-08-24 | 黑芝麻智能科技(上海)有限公司 | Method and system for calibrating driver distraction reference direction |
Non-Patent Citations (2)
| Title |
|---|
| 王振菊: "车载红外图像序列的行人目标分割与跟踪方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
| 陈建平: "基于车载视频的异常运动区域检测方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113822234B (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609522B (en) | Information fusion vehicle detection system based on laser radar and machine vision | |
| CN108196260B (en) | Method and device for testing multi-sensor fusion system of unmanned vehicle | |
| EP2023267B1 (en) | Object type determination apparatus, vehicle and object type determination method | |
| CN110745140B (en) | Vehicle lane change early warning method based on continuous image constraint pose estimation | |
| CN107490794A (en) | Object identification processing unit, object identification processing method and automated driving system | |
| EP2413304A1 (en) | Device for monitoring area around vehicle | |
| EP0567059A1 (en) | Object recognition system and abnormality detection system using image processing | |
| CN104573646A (en) | Detection method and system, based on laser radar and binocular camera, for pedestrian in front of vehicle | |
| EP2323098A1 (en) | Vehicle periphery monitoring device | |
| CN106650708A (en) | Visual detection method and system for automatic driving obstacles | |
| US10194059B2 (en) | Image processing apparatus and image processing method | |
| CN105480227B (en) | The method merged in active driving technology based on infrared radar with video image information | |
| JP2008507454A (en) | Road use vulnerable person protection system | |
| CN112464889A (en) | Road vehicle attitude and motion information detection method | |
| CN111580116A (en) | Method for evaluating target detection performance of vehicle-mounted system and electronic equipment | |
| CN110033621A (en) | A kind of hazardous vehicles detection method, apparatus and system | |
| CN113378741B (en) | Auxiliary sensing method and system for aircraft tractor based on multi-source sensor | |
| JP2006160116A (en) | Vehicle motion estimation device and moving body detection device | |
| JP2012123642A (en) | Image identifying device and program | |
| CN114758504B (en) | Online vehicle overspeed early warning method and system based on filtering correction | |
| CN107038406B (en) | Method for analyzing gestures | |
| CN115808324B (en) | Light safety management monitoring method and system for small and medium span bridges | |
| CN106874887A (en) | Based on the farm machinery navigation control method that farm environment is perceived | |
| CN108263389A (en) | A kind of vehicle front false target device for eliminating and method | |
| CN106846369A (en) | Vehicular turn condition discrimination method and device based on binocular vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |