A Real-Time Multi-Target Capture Framework Based on a Single PTZ Camera
Main Article Content
Keywords
PTZ camera, multi-target capture, path planning, object detection, intelligent surveillance
Abstract
To address the problems of insufficient target details and low multi-target capture efficiency in large-scale surveillance scenes, this paper proposes a real-time multi-target capture framework based on a single PTZ (Pan-Tilt-Zoom) camera. The proposed method integrates object detection, PTZ parameter estimation, and path scheduling to achieve rapid sequential capture of multiple targets. First, an object detection algorithm is used to locate targets in the scene. Then, the corresponding PTZ control parameters are estimated according to the pixel coordinates of each target, and feasible capture regions are constructed. Finally, a scheduling strategy combining greedy path planning and local optimization is adopted to generate a low-cost capture sequence for rapid PTZ switching among multiple targets. Experimental results demonstrate that the proposed framework can effectively reduce PTZ motion time and improve multi-target capture efficiency while maintaining stable operation in real-world environments. The proposed framework requires no additional hardware and has good practical deployment value for intelligent surveillance applications.
References
- [1] Del Bimbo A, Pernici F. Towards on-line saccade planning for high-resolution image sensing[J]. Pattern Recognition Letters, 2006, 27(15): 1826-1834.
- [2] Bellotto N, Sommerlade E, Benfold B, et al. A distributed camera system for multi-resolution surveillance[C]//2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC). IEEE, 2009: 1-8.
- [3] Liu Y, Lai S, Zuo C, et al. A Master‐Slave Surveillance System to Acquire Panoramic and Multiscale Videos[J]. The Scientific World Journal, 2014, 2014(1): 491549.
- [4] Chen C H, Yao Y, Page D, et al. Heterogeneous fusion of omnidirectional and PTZ cameras for multiple object tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(8): 1052-1063.
- [5] Natarajan P, Hoang T N, Low K H, et al. Decision-theoretic approach to maximizing observation of multiple targets in multi-camera surveillance[C]//AAMAS. 2012: 155-162.
- [6] Yi J, Acer U G, Kawsar F, et al. Argus: Enabling cross-camera collaboration for video analytics on distributed smart cameras[J]. IEEE Transactions on Mobile Computing, 2024, 24(1): 117-134.
- [7] Hu S, Shimasaki K, Jiang M, et al. A dual-camera-based ultrafast tracking system for simultaneous multi-target zooming[C]//2019 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, 2019: 521-526.
- [8] Hu S, Shimasaki K, Jiang M, et al. A simultaneous multi-object zooming system using an ultrafast pan-tilt camera[J]. IEEE Sensors Journal, 2021, 21(7): 9436-9448.
- [9] Li Q, Hu S, Shimasaki K, et al. An active multi-object ultrafast tracking system with CNN-based hybrid object detection[J]. Sensors, 2023, 23(8): 4150.
- [10] Zhang T, Li Z, Wang Q, et al. Dof-extended zoomed-in monitoring system with high-frame-rate focus stacking and high-speed pan-tilt adjustment[J]. IEEE Sensors Journal, 2024, 24(5): 6765-6776.
- [11] Li Q, Hu S, Shimasaki K, et al. An Ultrafast Multi-object Zooming System Based on Low-latency Stereo Correspondence[C]//2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024: 11552-11557.
- [12] Sommerlade E, Reid I. Information-theoretic active scene exploration[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2008: 1-7.
- [13] Salvagnini P, Pernici F, Cristani M, et al. Information theoretic sensor management for multi-target tracking with a single pan-tilt-zoom camera[C]//IEEE Winter Conference on Applications of Computer Vision. IEEE, 2014: 893-900.
- [14] Cai Y, Medioni G, Dinh T B. Towards a practical PTZ face detection and tracking system[C]//2013 IEEE Workshop on Applications of Computer Vision (WACV). IEEE, 2013: 31-38.
- [15] Melman S, Moses Y, Medioni G, et al. The multi-strand graph for a PTZ tracker[C]//2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 2015: 1-6.
- [16] Fang H, Liu H, Wen J, et al. Automatic visual enhancement of PTZ camera based on reinforcement learning[J]. Neurocomputing, 2025, 626: 129531.
- [17] Lin T Y, Maire M, Belongie S, et al. Microsoft coco: Common objects in context[C]//European conference on computer vision. Cham: Springer International Publishing, 2014: 740-755.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.