JP2001357385A - Automatic device for identifying person and vehicle or the like on road by ir camera - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an automatic device for identifying a person and a vehicle, etc., on a road by an IR camera, by which required road information is adequately and automatically detected on demand. SOLUTION: The automatic device is the one for identifying the person and the vehicle, etc., on the road through the use of the IR camera to continuously observe the road by the IR camera with high resolution, to specify an object such as an object dropped on the road, the vehicle, article or an animal by image-processing obtained temperature information, a size and a shape, etc., to make the information into a database with road temperature information as a key and to improve a specifying system.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an identification device for automatically identifying vehicles, people and other objects on a road.

[0002]

2. Description of the Related Art Conventionally, vehicles, people, and other objects on a road have been artificially identified by visually observing images taken by a visible camera such as an ITV. In such an identification method, there is a problem in that a necessary automatic road information cannot be obtained at any time in an automatic traveling system of a vehicle planned in the future. Therefore, it has been proposed to observe the road with an infrared camera, but in such a case, if the temperature fluctuates due to direct sunlight and shadows caused by the sun, an error occurs during image processing and identification is performed normally. There is a problem that you will not be.

[0003]

SUMMARY OF THE INVENTION Therefore, the present invention solves such a problem and provides necessary road information as needed.
Moreover, it is an object of the present invention to provide a device for identifying a person, a vehicle, and the like on a road, which can be automatically detected.

[0004]

SUMMARY OF THE INVENTION In order to achieve the above object, the present invention relates to an apparatus for identifying a person or a vehicle on a road, comprising: a pedestrian detecting means; a road surface state detecting means; The storage means and the invention according to claim 1, wherein the image from the infrared camera at a certain time, the first difference information of the image when there is nothing on the road, and the image from the infrared camera after information t time And, the second difference information of the image when there is nothing on the road is extracted, the object on the road is divided into a moving object and a stationary object, and the shape or the shape of the moving object and the stationary object, respectively. It is characterized by extracting temperature information and specifying an object.

According to a second aspect of the present invention, the temperature information is a characteristic temperature of the object. According to a third aspect of the present invention, the temperature information includes a road temperature and an object temperature. It is a characteristic temperature that is a temperature difference with respect to the temperature.

According to a fourth aspect of the present invention, the frequency distribution of the temperature is obtained from the image from the infrared camera, and the maximum frequency data which can be regarded as the data of the road portion based on the frequency distribution is reflected on the background image, and the road image is reflected on the road. It is characterized by identifying the above object.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS A first embodiment of the present invention shown in FIGS. 1 to 3 is capable of measuring temperature from blackbody emissivity.
An infrared camera having a sensitivity in a wavelength band of 帯 7 μm or 7-14 μm, a recording unit 2 for recording the image, and an image processing unit for processing the image are provided. Then, the image captured by the infrared camera is stored in a FIFO (first in first out) system. In the image processing unit, the road and the object on the road can be identified by comparing (difference) the video when there is nothing on the road immediately before the vehicle and the person appear on the road. I can do it. Further, the object can be classified into a moving object on the road or a stationary object, and the object can be specified from the display position and the size of the divided object on the image.

FIG. 1 shows the system and flow of each member of the embodiment that operates as described above. In such an embodiment, the road condition is observed by the infrared camera 1. And the observation result is NTSC (National Tel
evision Standard Cord).
The video signal is time-stamped by a video timer and recorded on a VTR (Video Tape Recorder).

Then, the VTR is reproduced, and a color signal correction, a VTR signal correction, and the like are performed on the reproduced image in a time base collector, A / D conversion is performed, and the image is captured by an image processing unit. 30Hz for memory
Is recorded in a cycle of A screen in which no object is present on the road among the images is registered in the recording unit in the processing unit as a background screen. Then, a difference process is performed between the subsequently input image and the registered image. As a result, an object that emerges as a difference is an object on the road. By repeating such processing, difference images are also accumulated at a cycle of 30 Hz.

Further, in order to identify this object, by comparing these stored images, a method as shown in FIGS. The stationary object is separated, and the object is specified from the temperature information of the object. 2-A to FIG. 2-G, FIG. 2-A is a drawing taken by the infrared camera at a certain time, FIG. 2-C is a drawing taken by the infrared camera after t time, and FIG. B and 2-D are drawings in a state where there is nothing on the road, and FIG. 2-A and 2-C are subjected to difference processing, and an object is recognized respectively. FIG. 2-A, 2-C, 2-E, 2-F
, 2 indicates a vehicle, and 3 indicates an obstacle or other object.

Next, FIG. 2G shows a difference between the current drawing in which the object is present and the drawing after the time t, so that the object on the screen is a moving object moving like a vehicle or another stationary object. This figure shows a state in which the object 3 is divided into objects, and FIG. As a method of this separation, if there is an object that moves using the difference processing, the current and t
The object after time remains, and if there is a stationary object, there is no trajectory on the drawing. The moving object may be displayed by displaying the result of the difference as it is, and the trajectory in which the stationary object is no longer displayed may be displayed again. Further, the temperature of each of the divided objects is compared with a temperature distribution from a temperature database stored in advance, and the moving object or the stationary object is specified.

Since it is known in advance whether the object is a moving object or a stationary object, the efficiency of specific recognition of the object using the temperature database is improved. Also, the background screen changes as a result of roads such as asphalt at the center of the background screen, weather, nighttime, temperature changes, and the like. By updating the background screen to be continuously observed at intervals as short as possible, the change can be absorbed. In addition, it is possible to create a database of the temperature difference between the road and the found object, and improve the identification rate of the object. Also, by using this database of the temperature difference, when the database of the absolute temperature is used, It is also possible to prevent erroneous recognition when the temperature of the road and the temperature of the vehicle or the person are similar. Further, as the identification of the object, a database in which the shape of the vehicle is registered may be used instead of using the temperature database.

The second embodiment of the present invention shown in FIG. 4 is similar in most parts to the configuration of the first embodiment. As in the first embodiment, the second embodiment is observed by an infrared camera and its image is obtained. Are taken into the image processing unit after A / D conversion and stored in the memory. In the image processing unit, the road and the object on the road can be identified by comparing (difference) the video when there is nothing on the road immediately before the vehicle and the person appear on the road. it can. At the same time, a temperature frequency distribution (histogram) of the screen is obtained, and data in a temperature range showing the maximum frequency is reflected in the identification processing, thereby coping with a temperature change. The image stored in the memory is an image proportional to the temperature, and the frequency distribution of the temperature is obtained from the image. If the range of monitoring is limited to the road portion, the maximum frequency can be regarded as the road. Therefore, by comparing this temperature with other temperatures, the road can be distinguished from other objects. Since this method can be performed for each screen, it can cope with a temperature change or the like.

[0014]

As described above, the present invention compares the images extracted from the infrared camera at a certain time and after t seconds,
Since the object is specified after the object is divided into the moving object and the stationary object, there is an effect that the ability to specify the object can be improved.

[Brief description of the drawings]

FIG. 1 is a diagram showing functions and signal flows of respective units according to a first embodiment of the present invention.

FIG. 2 is a view showing an obstacle detection concept according to the first embodiment;

FIG. 3 is a circuit configuration diagram of the above.

FIG. 4 is a diagram showing functions and signal flows of respective units according to a second embodiment of the present invention.

[Explanation of symbols]

 1 infrared camera 2 vehicle 3 object

 ────────────────────────────────────────────────── ─── Continued on the front page F term (reference) 5B057 AA16 BA02 DA06 DA12 DB02 DB06 DB09 DC06 DC09 DC14 DC23 DC30 DC33 5H180 AA01 AA21 CC02 CC04 EE11

Claims (4)

[Claims] An image from an infrared camera at a certain time,
Extracting first difference information of an image when there is nothing on the road, an image from the infrared camera after information time t, and second difference information of an image when there is nothing on the road, An object on the road is divided into a moving object and a stationary object on the road, and information on the shape or temperature of each of the moving object and the stationary object is extracted to identify the object. Automatic identification device for people, cars, etc. 2. The apparatus according to claim 1, wherein the temperature information is an inherent temperature of the object. 3. The infrared camera according to claim 1, wherein the temperature information is a temperature difference between the temperature of the road and the temperature of the object. Automatic identification device. 4. An object on a road is identified by taking a frequency distribution of temperature from an image from an infrared camera and reflecting data of a maximum frequency, which can be regarded as data of a road portion by the frequency distribution, in a background image. Automatic identification device for people, cars, etc. on the road by infrared camera.