-
A unified neural network for object detection, multiple object tracking and vehicle re-identification
Deep SORTwojke2017simple is a tracking-by-detetion approach to multiple ...
read it
-
TrackNet: Simultaneous Object Detection and Tracking and Its Application in Traffic Video Analysis
Object detection and object tracking are usually treated as two separate...
read it
-
Greedy Graph Searching for Vascular Tracking in Angiographic Image Sequences
Vascular tracking of angiographic image sequences is one of the most cli...
read it
-
Rethinking the competition between detection and ReID in Multi-Object Tracking
Due to balanced accuracy and speed, joint learning detection and ReID-ba...
read it
-
Automated Analysis of Femoral Artery Calcification Using Machine Learning Techniques
We report an object tracking algorithm that combines geometrical constra...
read it
-
Multi-hierarchical Independent Correlation Filters for Visual Tracking
For visual tracking, most of the traditional correlation filters (CF) ba...
read it
-
Limitation of Acyclic Oriented Graphs Matching as Cell Tracking Accuracy Measure when Evaluating Mitosis
Multi-object tracking (MOT) in computer vision and cell tracking in biom...
read it
Multi-object Tracking with a Hierarchical Single-branch Network
Recent Multiple Object Tracking (MOT) methods have gradually attempted to integrate object detection and instance re-identification (Re-ID) into a united network to form a one-stage solution. Typically, these methods use two separated branches within a single network to accomplish detection and Re-ID respectively without studying the inter-relationship between them, which inevitably impedes the tracking performance. In this paper, we propose an online multi-object tracking framework based on a hierarchical single-branch network to solve this problem. Specifically, the proposed single-branch network utilizes an improved Hierarchical Online In-stance Matching (iHOIM) loss to explicitly model the inter-relationship between object detection and Re-ID. Our novel iHOIM loss function unifies the objectives of the two sub-tasks and encourages better detection performance and feature learning even in extremely crowded scenes. Moreover, we propose to introduce the object positions, predicted by a motion model, as region proposals for subsequent object detection, where the intuition is that detection results and motion predictions can complement each other in different scenarios. Experimental results on MOT16 and MOT20 datasets show that we can achieve state-of-the-art tracking performance, and the ablation study verifies the effectiveness of each proposed component.
READ FULL TEXT
Comments
There are no comments yet.