Tracking moving objects in the real-time is a complex. A new paper proposes a multi-object visual color tracking algorithm using multi-threading in real-time using GPUs. A professor from The British University in Egypt presents the integration of a proposed enhanced multi-object color tracking, Partitioned Region Matching (PRM), and Spatial Region Graph (adjacency graph) for real-time multi-object tracking.
The paper mentions, “the problem of real-time object tracking is addressed by employing feature-based tracking technique that focuses on the integration of color feature tracking in regions of interest, and motion estimator which directly exploits computation of the region-level motion vectors through Partitioned Region Matching (PRM) that is based on the presence of gradients and semantically identify them according to their energy and other motion parameters. The preprocessed information are then converted to a spatial region graph (SRG) which is used as a starting point of a Markov Random Field (MRF) process, where regions are merged according to their semantics.”
The proposed method has been implemented using CUDA. Experimental results on GPU for a sequence of frames, each of 460×480 pixels, showed the implementation on GPU is 64 times faster than on CPU and confirmed the ability to process approximately 62 frames/s satisfying the necessary requirements for the correct subsequent tracking and reaching real-time performance that demonstrates the suitability of the proposed system for real-time video surveillance.
Read the entire research paper >>
Real-Time Multiple Moving Objects Tracking for Video Surveillance
Sep 09, 2015
Discuss (2)
Related resources
- DLI course: Building Real-Time Video AI Applications
- DLI course: Deep Learning for Industrial Inspection
- GTC session: Synchronize Multiple Sensors in Autonomous Machines
- GTC session: Open-World Segmentation and Tracking in 3D
- GTC session: Reliable Multi-Modal Perception in Complex Urban Multi-Agent Settings
- SDK: Optical Flow SDK