JP2012128693A - Video processing device, video processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To efficiently detect a specified object from a video image.SOLUTION: A video processing device includes a sensing unit for sensing an object from a video image, a determination unit for determining the direction of movement in which the object sensed by the sensing unit moves, and a detecting unit which, if the sensing unit senses plural objects, performs detection as to whether the plural objects are specified objects, in an order according to the direction of movement of the plural objects determined by the determination unit.

Description

  The present invention relates to a video processing apparatus, a video processing method, and a program for detecting a target object from a video.

  Conventionally, when a specific target such as a face or a human body is detected from an image, the target is detected by pattern matching processing. For example, in Patent Document 1, a plurality of local patterns are extracted using a matching pattern over the entire image while changing the size of the image, and each local feature is calculated. And it is determined whether it is a human body from the sum total of the result of having weighted the local feature-value. Moreover, in patent document 2, an object is efficiently detected by dividing | segmenting a screen into an area and performing a process according to the priority set to the area. Also, the priority of the section in which the target object is detected and the adjacent sections are set high.

JP 2009-211311 A JP 2008-234169 A

  However, when a human body is detected using the collation pattern over the entire screen, the processing load increases depending on the size of the screen. Further, for example, in the video of the surveillance camera, the subject moves in all directions, and the subject's face and human body characteristics are not always reflected in a direction that is easy to detect. In detecting a human body using a specific matching pattern, the detection accuracy changes according to the angle and size of the subject. Further, even if the screen is divided into sections, priorities are set based on past detection experiences, and human body detection processing is performed, the subject moves, so that an object detection result cannot be obtained efficiently. On the other hand, the monitoring camera is required to reduce the weight of the processing in order to realize real-time processing.

  The present invention has been made to solve the above-described problems, and an object thereof is to provide a video processing apparatus and a video processing method that can efficiently detect a target regardless of the angle and size of the subject. To do.

  In order to achieve the above object, the present invention provides a detection unit that detects an object from an image, a determination unit that determines a moving direction of an object detected by the detection unit, and the detection unit detects a plurality of objects. In this case, the apparatus includes a detecting unit that detects whether or not the plurality of objects are specific objects in an order corresponding to the moving direction of the plurality of objects determined by the determining unit.

  ADVANTAGE OF THE INVENTION According to this invention, it can detect about the object with high possibility that a specific object will be detected among the objects in an image | video. Therefore, the efficiency of the detection process for detecting a specific object from the video is improved.

1 is a diagram illustrating a configuration example of a video processing apparatus according to Embodiment 1. FIG. The figure for demonstrating the movement of the object in an image | video. The figure for demonstrating the moving direction angle | corner of the object in an image | video. The figure which shows a priority table. FIG. 6 is a flowchart for explaining the operation of the video processing apparatus according to the embodiment.

  Hereinafter, the present invention will be described in detail based on preferred embodiments with reference to the accompanying drawings. The configurations shown in the following embodiments are merely examples, and the present invention is not limited to the illustrated configurations.

<Example 1>
The configuration of the video processing apparatus of this embodiment will be described with reference to FIG. Each component shown in FIG. 1 may be configured as physically independent hardware, or may be configured as one or more instances of software having equivalent functions.

  The acquisition unit 101 acquires images captured by the processing target camera in chronological order. The acquisition unit 101 may acquire an image stored in a server or an external memory.

  The detection unit 102 detects an object from the image acquired by the acquisition unit 101. The detection unit 102 can detect a plurality of objects. The object information detected by the detection unit 102 includes the position of the object on the screen, a rectangle circumscribing the object, and the size of the object. For example, a background subtraction method can be used as an object detection method. The detection method is not limited to the background subtraction method, and any method that can acquire the above-described information may be used.

  The tracking unit 103 associates the object detected by the detection unit 102 from the past image acquired by the acquisition unit 101 and the object detected by the detection unit 102 from the current image acquired by the acquisition unit 101. The association can be performed by assigning an object ID assigned to an object detected from a past image to an object detected from the current image. Also, a new object ID is assigned to a newly appearing object.

  The priority determination unit 104 determines the priority of the area where the human body detection process is performed based on the size of the object detected by the detection unit 102 and the tracking result of the tracking unit 103. The priority determination by the priority determination unit 104 will be described with reference to FIGS. FIG. 2 is an example showing the moving direction of the object in the nth frame. Since the object with the object ID 12 has moved from the position 201 of the (n−1) th frame to the position 202 of the nth frame, the movement of the object ID 12 can be expressed as a position vector 203. Further, since the object with the object ID 6 has moved from the position 204 of the (n−1) th frame to the position 205 of the nth frame, the movement of the object ID 6 can be expressed as a position vector 206. In this embodiment, the moving direction angle is determined from the position vector between two frames. However, the moving direction angle may be determined from the inner product of the position vectors between a plurality of frames. When the detection unit 102 detects an object based on a motion vector, the moving direction of the object may be determined from the motion vector. In this way, the priority determination unit 104 determines the moving direction in which the object detected by the detection unit 102 moves.

FIG. 3 is an example showing the moving direction angle of the object. In this embodiment, the right direction is the positive x-axis direction, and the downward direction is the positive y-axis direction. The movement direction angle 302 of the position vector 301 is set so that the positive y-axis direction is 0 °. In the example shown in FIG. 3, the moving direction angle 302 is α. The priority determination unit 104 determines an evaluation value according to any one of the following formulas 1 to 4 according to the moving direction angle 302. And the priority determination part 104 sets a high priority in an order from the one where an evaluation value is small. When the moving direction angle α is 0 ° or more and less than 90 °, Equation 1 is obtained. When the moving direction angle α is 90 ° or more and less than 180 °, Equation 2 is obtained. When 180 ° or more and less than 270 °, Equation 3 is obtained. In the case of (4), Formula 4 is used. In the case of the same evaluation value, the priority is set in order from the smallest object ID.
(Formula 1) Val dir = α
(Formula 2) Val dir = | α−180 |
(Formula 3) Val dir = α−180
(Formula 4) Val dir = | α-360 |

  In this way, the priority determination unit 104 sets the priority of the object moving in the vertical direction of the screen higher than the priority of the object moving in the horizontal direction of the screen. The priority setting method is not limited to the above. If the priority is set higher in order from the larger evaluation value, the priority of the object moving in the horizontal direction of the screen can be set higher than the priority of the object moving in the vertical direction of the screen. The priority may be set according to the moving direction angle 302 without using the above formulas 1 to 4. Thus, when the detection unit 102 detects a plurality of objects, the priority determination unit 104 determines the priority for the objects according to the determined moving directions of the plurality of objects.

  Next, the priority determination unit 104 determines the size of the objects detected in order from the higher priority. When the size of the object is smaller than the predetermined threshold, the priority determination unit 104 sets a skip flag indicating that the detection process described later is not performed. The threshold value of the object size is a value set in advance in accordance with an instruction from the user or the like. An example showing the result of setting the priority and the skip flag is shown in FIG. The information shown in FIG. 4 is held in a storage area (not shown). In the present embodiment, the skip flag is set based on the size of the object detected by the detection unit 102, but is not limited to the above. The skip flag can be set to separate objects such as the moving direction angle, object height, object width, object area change, object shape aspect ratio, which is the ratio of object height to width, and object moving speed. Anything can be used as long as it is set based on the attribute of the object. In this way, when the detection unit 102 detects a plurality of objects, the priority determination unit 104 determines whether the feature amount of the object satisfies a predetermined condition in order from the highest priority. To decide. By not performing detection processing on an object for which a skip flag has been set in this way, the detection probability for detecting a desired object from a plurality of objects detected by the detection unit 102 can be improved. In addition, the processing amount for detecting a desired object from a plurality of objects detected by the detection unit 102 can be reduced. However, in the present invention, the detection process using the skip flag is not an essential process. After determining the priority of the object detected by the detection unit 102, a detection process described later may be performed without setting the skip flag.

  The detection unit 105 detects a human body by performing a pattern matching process on the object region detected by the detection unit 102. The detection method is not limited to the method using pattern matching processing. In the present embodiment, the detection unit 105 detects a human body in order from an object having a higher priority and the priority determined by the priority determination unit 104 and the skip flag are not set. In this way, the detection unit 105 determines whether to detect whether the object detected by the detection unit 102 is a specific object, based on the skip flag set by the priority determination unit 104. When the skip flag is not set, the detection unit 105 detects the human body in order from the object with the highest priority. In this way, when the detection unit 102 detects a plurality of objects, the detection unit 105 detects whether the plurality of objects are specific objects in the order according to the priority determined by the priority determination unit 104. Do. This priority is determined according to the moving direction of the object. For example, when the detection unit 105 detects a human body in a captured image, the object approaching the camera being photographed is prioritized over the object moving in the other direction to determine whether it is a human body. An object that moves away from the camera may be given the same priority as an approaching object. Whether or not the camera approaches the camera is determined by an angle based on the moving direction in the video, that is, the vertical direction in the video. Further, the order of detection can be directly determined from the angle without determining the priority. For example, when a face image of a specific person is used as a pattern used for pattern matching, priority is given to an object approaching the camera as described above, so that an object whose face faces the camera direction is directed to another direction Pattern matching can be performed with higher priority than the above. In this way, by performing the detection with priority on the image in which the feature of the object appears, the accuracy of detecting the desired object can be increased. In addition, detection processing can be performed efficiently because detection processing is performed in preference to an object with a high probability that a desired object is detected. In this embodiment, the detection target is a human body, but the detection target is not limited to the human body. The detection target may be a specific target such as a face, a car, an animal, or the like. Furthermore, a detection unit that detects a plurality of types of specific objects may be provided, and a plurality of detection processes may be performed simultaneously. Further, depending on the attribute of the object used for setting the skip flag, such as the size of the object and the aspect ratio, only a predetermined process among a plurality of specific object detection processes may be selected and the detection process may be performed. For example, it is assumed that the detection unit 105 includes a human body detection unit and a vehicle detection unit. The user presets the minimum size of the vehicle appearing on the screen as a threshold value. When the size of the object detected by the detection unit 102 is smaller than the minimum vehicle size, the detection unit does not perform the process in the vehicle detection unit, but performs only the process in the human body detection unit. On the other hand, when the size of the object is larger than the threshold value, processing in the car detection unit is performed. Further, when the size of the object is larger than the threshold value, there is a possibility that a plurality of people act as a group and are detected as one object, so the processing in the human body detection unit is also performed. In this manner, the detection unit 105 performs detection by selecting which of a plurality of specific objects is detected according to the feature amount of the object detected by the detection unit 102. Thereby, a plurality of detection objects can be detected efficiently.

  The abort unit 106 determines the abort of the human body detection process by the detection unit 105 according to the processing elapsed time. The elapsed time threshold value for determining the discontinuation is a value set in advance in accordance with an instruction from the user or the like. The decision to abort the detection process is not limited to that performed based on the elapsed time from the start of the process. The detection process abortion may be determined from the number of human bodies detected by the detection unit 105, the number of times the detection unit 105 has executed human body detection processing, and the like. The output unit 107 outputs the detection result of the detection unit 102, the tracking status of the tracking unit 103, and the detection result of the detection unit 105 to the outside.

  The operation of the video processing apparatus according to this embodiment is shown in the flowchart of FIG. When the video processing apparatus includes a processor and a memory, the processing flow in FIG. 5 shows a program for causing the processor to execute the procedure shown in FIG. The processor built in the video processing apparatus is a computer, and executes a program read from a memory built in the video processing apparatus. The memory built in the video processing apparatus is a recording medium on which the program is recorded so that the processor can read it.

  In f1, the acquisition unit 101 determines whether to continue or end the image acquisition (f1). The determination of step f1 can be made based on a user instruction input from an input unit (not shown). Alternatively, the image acquisition may be terminated when a desired object is detected. The determination method is not limited to these, and is not particularly limited. When the detection process is continued, the acquisition unit 101 acquires an image from the outside (f2). Next, the detection unit 102 performs detection processing on the image acquired by the acquisition unit 101 (f3). Subsequently, the detection processing result is determined (f4). If no object is detected (if f4 is no), the process returns to f1. When an object is detected (if f4 is yes), the tracking unit 103 performs object tracking processing (f5). And the priority determination part 104 determines the priority of the object which performs a detection process (f6). Next, it is determined whether to continue or end the detection process according to the determination of the truncation unit 106 (f7). For example, when the detection unit 102 detects a plurality of objects in the screen, the truncation unit 106 determines whether to perform the detection process for the second object after performing the detection process for the first object. . The abort unit 106 can determine whether or not to continue the detection process according to the number of human bodies detected by the detection unit 105, the number of times the detection unit 105 executes the human body detection process, and the like. Alternatively, the truncation unit 106 can make the determination in step f7 based on a user instruction input from an input unit (not shown). Alternatively, the detection process may be terminated when a desired object is detected. The determination method is not limited to these, and is not particularly limited. When the detection process is continued (if yes in f7), the human body detection process is performed in the detection unit 105 in order from the object area with the highest priority according to the determined priority. When the detection process is terminated (if f8 is no), the process returns to f1.

  With the above configuration, it is possible to detect an object that is highly likely to detect a specific object among objects in the video. Therefore, the efficiency of the detection process for detecting a specific object from the video is improved.

<Other examples>
The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

102 detection unit 104 priority determination unit 105 detection unit

Claims (8)

Detection means for detecting an object from the image;
Determining means for determining a moving direction in which the object detected by the detecting means moves;
And detecting means for detecting whether the plurality of objects are specific objects in an order corresponding to the moving direction of the plurality of objects determined by the determining means when the detecting means detects a plurality of objects. A video processing apparatus characterized by that.   2. The detection unit according to claim 1, wherein the detection unit performs the detection by selecting which one of a plurality of specific objects is detected according to a feature amount of the object detected by the detection unit. Video processing equipment. Detection means for detecting an object from the image;
Determining means for determining a moving direction in which the object detected by the detecting means moves;
A determination unit configured to determine whether or not feature quantities of the plurality of objects satisfy a predetermined condition in an order according to a moving direction of the plurality of objects determined by the determination unit when the detection unit detects a plurality of objects; ,
An image processing apparatus comprising: a detection unit that determines whether or not to detect whether the object detected by the detection unit is a specific object, based on a determination result of the determination unit.   The feature amount is at least one of the size of the object, the moving speed of the object, the ratio of the height and width of the object, the amount of change in the area of the object, and the moving direction of the object. The video processing apparatus according to claim 3. A detection step in which the detection means detects an object from the video;
A determining step for determining a moving direction in which the object detected in the detecting step moves;
When the detection unit detects a plurality of objects in the detection step, detection is performed to detect whether the plurality of objects are specific objects in an order corresponding to the moving direction of the plurality of objects determined in the determination step. And a video processing method. A detection step in which the detection means detects an object from the video;
A determining step for determining a moving direction in which the object detected in the detecting step moves;
When the detection means detects a plurality of objects in the detection step, whether to detect whether the plurality of objects are specific objects in an order according to the moving direction of the plurality of objects determined in the determination step And a detection step for determining whether or not. On the computer,
A detection procedure for detecting an object from the image;
A determination procedure for determining a moving direction in which the object detected in the detection procedure moves;
When a plurality of objects are detected in the detection procedure, a detection procedure for detecting whether the plurality of objects are specific objects is executed in an order corresponding to the moving direction of the plurality of objects determined in the determination procedure. Program for. On the computer,
A detection procedure for detecting an object from the image;
A determination procedure for determining a moving direction in which the object detected in the detection procedure moves;
A determination procedure for determining whether or not feature quantities of the plurality of objects satisfy a predetermined condition in an order corresponding to a moving direction of the plurality of objects determined in the determination procedure when a plurality of objects are detected in the detection procedure; ,
A program for executing a detection procedure for determining whether or not to detect whether an object detected in the detection procedure is a specific object based on a determination result in the determination procedure.

Images