Search

KR-20260066287-A - System and method for multiple object detection using a single PTZ CCTV

KR20260066287AKR 20260066287 AKR20260066287 AKR 20260066287AKR-20260066287-A

Abstract

The present invention aims to provide a multi-object detection system and method using a single PTZ CCTV that enables object tracking and direction measurement through PTZ control with minimal cost and loss, by implementing optimized movement of the PTZ CCTV to find moving objects first. A multi-object detection system using a single PTZ CCTV according to one embodiment of the present invention may include a zigzag scheduling module that divides a shooting range into zones of a certain size and acquires captured images while moving in a zigzag pattern through each zone; an image preprocessing module that processes the captured images; a moving object detection module that identifies and detects moving objects in the captured images; an object movement direction recognition module that recognizes the movement direction of the detected moving objects; a storage module that stores information of the moving objects in a database; and a control module that controls the tracking of the moving objects with a single PTZ CCTV and sets a tracking priority among the objects when there are multiple moving objects.

Inventors

  • 조운
  • 안건태
  • 이진우
  • 박지훈

Assignees

  • 재단법인 포항산업과학연구원

Dates

Publication Date
20260512
Application Date
20241104

Claims (20)

  1. A zigzag scheduling module that divides the shooting range into zones of a fixed size and acquires captured images by moving through each zone in a zigzag pattern; An image preprocessing module for processing the above-mentioned captured image; A moving object detection module that identifies and detects moving objects in the above-mentioned captured image; Object movement direction recognition module that recognizes the movement direction of a detected moving object; A storage module that stores information of the above-mentioned moving object in a database; and A control module that controls the tracking of the moving object using a single PTZ CCTV and sets a tracking priority among each object when there are multiple moving objects; Multi-object detection system using a single PTZ CCTV.
  2. In paragraph 1, The above zigzag scheduling module is, Starting recording from the top-left point within the entire range where the PTZ CCTV can move, scheduling proceeds in a zigzag direction until the first object is found, and upon completion of tracking the object, returns to the top-left point to repeat the zigzag scheduling. Multi-object detection system using a single PTZ CCTV.
  3. In paragraph 1, The above image preprocessing module includes a noise removal unit, and The above noise removal unit operates as a 2x2 filter when the brightness of the acquired image is greater than or equal to a set threshold, and operates as a 3x3 filter when the brightness of the acquired image is less than the set threshold. Multi-object detection system using a single PTZ CCTV.
  4. In paragraph 3, The above image preprocessing module is, A brightness adjustment unit further comprising adjusting the brightness of the image that has passed through the noise removal unit to match the cumulative average brightness value from a specific time in the past to the present. Multi-object detection system using a single PTZ CCTV.
  5. In paragraph 4, The above image preprocessing module is, A shadow removal unit further comprising determining the presence or absence of shadows in the brightness-adjusted image and obtaining an image with shadows removed, Multi-object detection system using a single PTZ CCTV.
  6. In paragraph 1, The above moving object detection module is, Identifying objects by reflecting together object detection results using artificial intelligence and object detection results using the Cam-shift method, Multi-object detection system using a single PTZ CCTV.
  7. In paragraph 6, The above moving object detection module is, If the intersection area of the first area detected as an object using the artificial intelligence above and the second area detected as an object using the Cam-shift method above is 70% or more of the union area of the first area and the second area, the union area is specified as an object. Multi-object detection system using a single PTZ CCTV.
  8. In paragraph 6, The above moving object detection module is, If the intersection area of the first area detected as an object using the artificial intelligence and the second area detected as an object using the Cam-shift method is less than 70% of the union area of the first area and the second area, the intersection area is specified as an object. Multi-object detection system using a single PTZ CCTV.
  9. In paragraph 1, The above object movement direction recognition module is Correcting and determining the movement direction and movement speed of the object according to the direction of the object's head and the movement of a part connected to the object's body, using the initial movement speed and movement direction of the object detected by the above-mentioned moving object detection module. Multi-object detection system using a single PTZ CCTV.
  10. In paragraph 1, The above storage module is, Storing at least one of the image, coordinates, shooting time, direction of movement, and speed of movement of the above-mentioned moving object in the database, Multi-object detection system using a single PTZ CCTV.
  11. In paragraph 1, The above control module is, When the above moving object is singular, controlling the operation of the PTZ CCTV so that the above moving object is positioned at the center of the frame, Multi-object detection system using a single PTZ CCTV.
  12. In paragraph 1, The above control module is, Among the plurality of moving objects, determining the object that will first move out of the entire shooting range of the PTZ CCTV and tracking the object. Multi-object detection system using a single PTZ CCTV.
  13. In Paragraph 12, The above plurality of moving objects includes a first object and a second object, and The control module calculates the remaining departure time of the first object by measuring the movement speed of the first object and the distance remaining to the boundary line of the maximum shooting range in the direction of movement, calculates the remaining departure time of the second object by measuring the movement speed of the second object and the distance remaining to the boundary line of the maximum shooting range in the direction of movement, and compares the remaining departure times of each of the first object and the second object. Multi-object detection system using a single PTZ CCTV.
  14. In Paragraph 13, The above control module is, Prioritizing the tracking of the object with the shorter remaining departure time among the first object and the second object. Multi-object detection system using a single PTZ CCTV.
  15. In Paragraph 14, The above control module is, If the object prioritized for tracking moves out of the maximum shooting range, the object with the shortest remaining departure time among the remaining objects is selected and tracked. Multi-object detection system using a single PTZ CCTV.
  16. A step of dividing the shooting range into zones of a certain size and acquiring captured images while moving through each zone in a zigzag pattern; A step of preprocessing the above-mentioned captured image; A step of identifying and detecting a moving object in the above-mentioned captured image; A step of recognizing the direction and speed of movement of the moving object in the above-described captured image; A step of storing information about the above-mentioned moving object in a database; and Controlling the tracking of the moving object using a single PTZ CCTV, and, if there are multiple moving objects, setting a tracking priority among each object; comprising Multiple object detection method using a single PTZ CCTV.
  17. In Paragraph 16, The step of acquiring the above-mentioned captured image is, Step of starting shooting from the uppermost left point of the maximum shooting area; Step of shooting in a zigzag direction up to the lowest right point; and A step of returning to the uppermost left point and repeating the shooting; comprising, Multiple object detection method using a single PTZ CCTV.
  18. In Paragraph 16, The step of preprocessing the above-mentioned captured image is, A step of removing noise from the above-mentioned captured image; A step of adjusting the brightness of the above-mentioned captured image; and A step of removing shadows within the above-mentioned captured image; comprising Multiple object detection method using a single PTZ CCTV.
  19. In Paragraph 16, The step of identifying and detecting moving objects in the above-mentioned captured image is, A step of detecting objects using artificial intelligence; A step of detecting an object using a cam-shift method; and A step of identifying an object according to the ratio of the intersection area to the union area of a first area detected as an object using the artificial intelligence and a second area detected as an object using the Cam-shift method; comprising Multiple object detection method using a single PTZ CCTV.
  20. In Paragraph 16, The step of recognizing the direction of movement of the object in the above-mentioned captured image is to... A step of zooming in on a PTZ CCTV using the initial movement speed and movement direction of an object detected by the above-mentioned moving object detection module; A step of correcting and determining the direction of movement of the object according to the direction of the head portion of the object and the movement of a part connected to the body of the object; A step of zooming out of a single PTZ CCTV; and A step of correcting and determining the movement speed of the above object; comprising Multiple object detection method using a single PTZ CCTV.

Description

System and method for multiple object detection using a single PTZ CCTV The present invention relates to a multi-object detection system and method using a single PTZ CCTV. PTZ CCTV is a type of CCTV that utilizes panning, tilting, and zooming. Compared to conventional fixed CCTVs, it offers a wider range of controllable movement, making it advantageous for obtaining more information. Generally, when detecting objects using a single PTZ CCTV, methods are employed where only the first object is tracked and others are not, or only the object with the highest accuracy is tracked. While these approaches are effective for object detection, they suffer from data loss when multiple objects appear, leading to a problem of continuously accumulating loss. Additionally, although this is addressed by installing multiple PTZ CCTVs to locate multiple objects, it presents issues because it requires as many cameras as there are objects, and the number of objects that will appear is unpredictable. FIG. 1 is a conceptual diagram schematically illustrating a multi-object detection system using a single PTZ CCTV according to one embodiment of the present invention. FIG. 2 is a block diagram schematically illustrating a multi-object detection system and method using a single PTZ CCTV according to an embodiment of the present invention. Figure 3 is a diagram showing the control of a PTZ CCTV by a zigzag scheduling module. Figure 4 is a diagram showing a sample of an image that has passed through an image preprocessing module. Figure 5 is a diagram showing a cam-shift object detection algorithm. Figures 6 and 7 are diagrams illustrating the object region determination and specific algorithm of the moving object detection module. Figures 8 and 9 are diagrams illustrating the recognition of the object movement direction and speed of the object movement direction recognition module. Figure 10 is the experimental result of applying the recognition of the object movement direction and speed of Figures 8 and 9 to a multi-object detection system using a single PTZ CCTV according to one embodiment of the present invention. Figures 11 and 12 are diagrams illustrating multi-object tracking of a control module. Figure 13 is the experimental result of applying the multi-object tracking situation of Figures 10 and 11 to a multi-object detection system using a single PTZ CCTV according to one embodiment of the present invention. FIG. 14 is a diagram illustrating an exemplary computing environment in which a multi-object detection system and method using a single PTZ CCTV according to an embodiment of the present invention can be implemented. Preferred embodiments of the present invention will be described below with reference to the attached drawings. However, embodiments of the present invention may be modified in various other forms, and the scope of the present invention is not limited to the embodiments described below. In addition, embodiments of the present invention are provided to more fully explain the present invention to those with average knowledge in the relevant technical field. In drawings, the shapes and sizes of elements may be exaggerated for clearer explanation. In describing the embodiments of the present invention, if it is determined that a detailed description of known technology related to the present invention may unnecessarily obscure the essence of the present invention, such detailed description will be omitted. Furthermore, the terms described below are defined considering their functions in the present invention, and these may vary depending on the intentions or conventions of the user or operator. Therefore, such definitions should be based on the content throughout this specification. The terms used in the detailed description are merely for describing the embodiments of the present invention and should not be limited in any way. Unless explicitly stated otherwise, expressions in the singular form include the meaning of the plural form. In this description, expressions such as “include” or “equipped” are intended to refer to certain characteristics, numbers, steps, actions, elements, parts or combinations thereof, and should not be interpreted to exclude the existence or possibility of one or more other characteristics, numbers, steps, actions, elements, parts or combinations thereof other than those described. Unless otherwise specifically defined in the specification of the present invention, % units mean weight %. In this specification, terms such as 'top', 'upper', 'upper surface', 'lower', 'lower surface', 'lower surface', and 'side surface' are based on the drawings and may actually vary depending on the direction in which the elements or components are arranged. Additionally, throughout the specification, when it is said that one part is 'connected' to another part, this includes not only cases where they are 'directly connected,' but also cases where they are 'indirectly connected' with other elements in