The future of smart city analytics requires state-of-the-art software methods, specialized compute and efficient edge hardware to enable real-time tracking and edge AI analysis for applications such as pedestrian safety. In this Tech Talk we will explore state-of-the-art tracking methods including motion prediction tracking, identity assignment, and reidentification techniques. The …
The machine vision team at Arcturus (Arcturus Networks Inc., Toronto) published its Multiple Object Tracking (MOT) benchmark numbers today. Arcturus reported that its second generation BrinqTraq (BQTQ) software achieved a Multiple Object Tracking Accuracy (MOTA) score of 79.5 with a Detection Accuracy (DetA) of 65.0 for the MOT20 multiple object …
BrinqTraq Software Improves Accuracy of Vision Based Object Tracking on Edge Devices Arcturus (Arcturus Networks Inc., Toronto) released its Multiple Object Tracking (MOT) benchmark numbers today. Arcturus reported that its BrinqTraq (BQTQ) software achieved a MOTA benchmark score of 77.2 for MOT16 and 77.7 for MOT17 challenges. The results represent …