JPH04337900A - Instrument for measuring vehicle movement - Google Patents

Abstract

PURPOSE:To avoid the addition of data in the back periphery part of another vehicle being adjacently running to video data of the object vehicle in an instrument measuring vehicle movement from a video image. CONSTITUTION:Digital data for two screens where the movement of the object vehicle is image-picked-up at fixed time interval is stored in image memories 3 and 4 corresponding to the respective screens, background data is stored in the image memory 5, an image data processing part 8 executes a processing through the use of the stored data, the processing result is written in the image memory 6, image data of the object vehicle is picked-up and the processing is successively executed so that the pursuit of the vehicle, running speed, etc., are outputted.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a vehicle dynamic measurement device that measures and collects necessary traffic information such as the speed of vehicles passing on a road, the number of vehicles passing by, and the type of vehicle (normal vehicle/large vehicle, etc.).

0002

2. Description of the Related Art Conventionally, this type of vehicle dynamic measuring device processes only the positive component of the difference result in order to remove background data from, for example, original image data that captures the movement of a vehicle on a road. Vehicle speed, number of passing vehicles, vehicle type (normal vehicle/
It is configured to be able to measure and output data such as large vehicles, etc.

0003

[Problems to be Solved by the Invention] However, in the conventional vehicle dynamic measurement device described above, even if image processing is performed using only positive components, it is not possible to remove all unnecessary images. The trailing edge of the image of a vehicle is detected, and in the case of a vehicle traveling at high speed or a large vehicle, the image may be determined to be a moving vehicle, resulting in an erroneous detection.

Furthermore, since image processing is performed using only positive components, in the case of a video image with a small brightness difference from a black vehicle or a road surface, it is not possible to completely extract the vehicle image using a normal processing screen. There was a problem that it could not be detected in some cases.

[0005] The present invention solves these conventional problems, and is capable of accurately measuring the speed of a vehicle without being affected by the images of other vehicles traveling in adjacent lanes or the brightness of the vehicle to be measured.
The objective is to provide a vehicle dynamic measurement device that measures and collects necessary traffic information such as the number of passing vehicles and vehicle types (normal vehicles/large vehicles, etc.).

[0006]

SUMMARY OF THE INVENTION The present invention is characterized in that it is determined for each pixel whether or not the result of frame difference processing with expansion processing is valid based on the result of background difference processing.

[0007] Furthermore, a processing screen is created in such a way that weighting can be changed between pixels made effective by background difference processing, pixels made effective by frame difference processing with dilation processing, and pixels made effective by both. It is characterized by this.

[0008]

[Operation] According to the present invention, firstly, by determining whether or not to enable frame difference based on the result of background difference processing in pixel units, the trailing edge of the image of a vehicle traveling in an adjacent lane is parts can be removed. Second, accurate vehicle measurements can be made without being affected by images of vehicles traveling in adjacent lanes. Thirdly, by changing the weighting of the processing results for each pixel based on the difference results, it is possible to create a more reliable processing screen, and it is possible to extract black vehicles etc. with a small brightness difference from the road surface. Therefore, it is possible to accurately track and measure vehicles, and to measure and collect accurate traffic information.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 shows the structure of a first embodiment of the present invention.

In FIG. 1, 1 is a video camera, 2 is a vehicle dynamic measuring device main body (hereinafter simply referred to as the device main body), and 3 is a video camera.
Image memories 6 to 6 store input images 1 to 4, respectively. 7 is a video data A/D conversion section, 8 is an image data processing section, and 9 is a data output section.

Next, the operation of the above embodiment will be explained. Video information of the vehicle 10 captured using the video camera 1 is transmitted to the device main body 2. The device main body 2 converts the input video information into digital data using the video data A/D converter 7, and converts the input video information into digital data, which is imaged at a certain time interval.
Digital data for a screen is stored in image memories 3 and 4, respectively. Further, the image memory 5 stores information (background data) regarding a state in which the vehicle 10 is not present.

[0012] Using the data in these image memories 3, 4, and 5, the image data processing unit 8 writes the processing results into the image memory 6 by using only the positive components of the background difference processing and the frame difference processing with expansion processing. , the vehicle 10 is extracted from the image data, and by performing this process continuously, the data output unit 9 outputs the vehicle's tracking, running speed, etc., and also determines the current road condition and uses this information. Update the background data based on.

FIG. 2 is an operational flowchart of the basic processing of the above embodiment, and will be described below with reference to this.

[0014] Here, the image data (pixels) to be processed are m
The image memory data that stores the new (NEW) image is N (coordinates i, j, the same below), the image memory data that stores the old (OLD) image is O (i, j), and the background data is The stored image memory data is H (i, j), the area for storing the background difference result is a (i, j), the area for storing the frame difference result is b (i, j), background difference processing and dilation. The area for storing the results of frame difference processing with processing is c(i, j), and the threshold value for determining whether to perform background difference processing and frame difference processing with expansion processing is TH1.
, the threshold for frame difference processing with dilation processing is also set to TH2.
, the background difference threshold is set to TH3.

First, step (hereinafter abbreviated as S) (
After initializing the coordinates i and j in S1) and (S2), respectively,
The background screen data is subtracted from the new image data for each pixel and the background difference is stored in the extraction area a (S3). next,
Using the threshold TH1, a(i,
j) (S4). If it is less than the threshold TH1, "0" is written in the processing result storage area c(i,j) (S5).

If the threshold value TH1 or more is exceeded, the frame difference is subtracted from the new image data by the old image data and stored in the extraction area b (S6), and it is determined whether the value is greater than or equal to the threshold value TH2 for frame difference processing with expansion processing. is determined (S7). If the threshold value TH2 or more, “1” is stored in the processing result storage area c(i,j) of the image memory 6 (FIG. 1).
” is written with expansion processing (S8).

If it is less than the threshold TH2, the background difference result a(i,j) is compared with the background difference threshold TH3 (S9), and if it is more than the threshold TH3, the processing result storage area c( "1" is written in (i, j) (S10). In addition, if the threshold value TH3 or less, the processing result storage area c
"0" is written in (i, j) (S5). This is m rows n
Perform this for all image data in the column (S1, S2
, S11, S12, S13, S14).

According to the above embodiment, the trailing edge portion of the image of a vehicle traveling in an adjacent lane is removed by determining whether or not to enable frame difference based on the result of background difference in units of pixels. It has the advantage of being able to Furthermore, accurate vehicle measurements can be made without being affected by images of vehicles traveling in adjacent lanes.

FIG. 3 is a flowchart of processing screen creation processing as a second embodiment.

The image data to be processed is arranged in m rows and n columns, image memory data storing the new image is N(i,j), image memory data storing the old image is O(i,j), and background data is stored. H(i,j) is the image memory data that has been created, a(i,j) is the area that stores the background difference results, b(i,j) is the area that stores the frame difference results, and an area that stores the processed screen. is c(i,j), the threshold for frame difference processing with dilation processing is TH1, and the threshold for background difference is TH2.

First, the background screen data is subtracted from the new image data for each pixel to obtain the background difference, and the area a(i,
j) (S3), then subtract the old image data from the new image data to create a frame difference and store it in area b(i,
After storing it in area X (i) on the processing screen (S4),
, j) (S5). Then, a(i,j) is compared with the threshold value TH1 of the frame difference result and the frame difference process with expansion process (S6). and threshold TH1
In the above case, "80h" is written on the processing screen with expansion processing (S7).

Next, the background difference result and the background difference threshold T
A comparison is made with H2 (S8), and if it is greater than the threshold TH2, a logical sum of "7Fh" is written on the processing screen (
S9). By doing this, the pixel that became effective in the background difference becomes "7Fh", the pixel that becomes effective in the frame difference processing with expansion processing becomes "80h", and the pixel that becomes effective in both becomes "FFh", can be distinguished.

This is done for all the image data in m rows and n columns (S1, S2, S10, S11, S12, S13
).

As described above, according to this embodiment, by changing the weighting of the processing results for each pixel based on the difference results, a more reliable processing screen can be created.
It becomes possible to extract black vehicles and the like with a small difference in brightness from the road surface, allowing accurate vehicle tracking and measurement, and accurate measurement and collection of traffic information.

[0025]

Effects of the Invention As explained above, the vehicle dynamic measurement device of the present invention determines whether or not to enable frame difference based on the result of background difference in units of pixels. The trailing edge portion of the image can be removed. In addition, it is possible to accurately measure a vehicle without being affected by images of vehicles running in adjacent lanes (claim 1), and by changing the weighting of processing results based on the difference results for each pixel, more reliable It is possible to create a processed screen, it is possible to extract black vehicles with a small difference in brightness from the road surface, it is possible to accurately track and measure vehicles, and it is possible to measure and collect accurate traffic information. 2).

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the configuration of a first embodiment of the present invention.

FIG. 2 is a flowchart illustrating validity determination of a frame difference in the embodiment of FIG. 1;

FIG. 3 is a flowchart of processing screen creation processing in the second embodiment.

[Explanation of symbols]

1...Video camera, 2...Vehicle dynamic measurement device main body,
3-6... Image memory, 7... A/D conversion section, 8
...Image data processing unit, 9...Output unit, 10...Vehicle.

Claims (2)

[Claims] Claim 1: Performing background subtraction processing and frame subtraction processing with dilation processing on video image data that captures the movement of road vehicles, and creating a processed screen using only the positive components thereof;
A vehicle dynamics measuring device that measures and collects vehicle dynamics from the processed screen, the vehicle dynamics determining device determining whether to enable the result of frame difference processing with expansion processing based on the result of background difference processing. Measuring device. 2. Performing background subtraction processing and frame subtraction processing with dilation processing on video image data capturing the movement of a vehicle on the road, and creating a processed screen using only the positive components thereof,
In a vehicle dynamic measurement device that measures and collects vehicle dynamics from the processed screen, pixels that are enabled by background difference processing, pixels that are enabled by frame difference processing with expansion processing, and pixels that are both enabled. A vehicle dynamic measurement device characterized by creating a processing screen so that weighting can be changed by and.