A Review of Deep Learning-Based Visual Multi-Object Tracking Algorithms for Autonomous Driving

Abstract

Multi-target tracking, a high-level vision job in computer vision, is crucial to understanding autonomous driving surroundings. Numerous top-notch multi-object tracking algorithms have evolved in recent years as a result of deep learning’s outstanding performance in the field of visual object tracking. There have been a number of evaluations on individual sub-problems, but none that cover the challenges, datasets, and algorithms associated with visual multi-object tracking in autonomous driving scenarios. In this research, we present an exhaustive study of algorithms in the field of visual multi-object tracking over the last ten years, based on a systematic review approach. The algorithm is broken down into three groups based on its structure: methods for tracking by detection (TBD), joint detection and tracking (JDT), and Transformer-based tracking. The research reveals that the TBD algorithm has a straightforward structure, however the correlation between its individual sub-modules is not very strong. To track multiple objects, the JDT technique combines multi-module joint learning with a deep network framework. Transformer-based algorithms have been explored over the past two years, and they have benefits in numerous assessment indicators, as well as tremendous research potential in the area of multi-object tracking. Theoretical support for algorithmic research in adjacent disciplines is provided by this paper. Additionally, the approach we discuss, which uses merely monocular cameras rather than sophisticated sensor fusion, is anticipated to pave the way for the quick creation of safe and affordable autonomous driving systems.

BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking

“…Multiple object tracking (MOT) is one of the most important problem in computer vision and has applications in areas of autonomous robotics [20,50], autonomous driving [12,24,43,52] and smart cities [8,44,52,72]. The problem consists of determining the position and identity of each object of interest (e.g.…”

A Lightweight Vehicle Detection Method Fusing GSConv and Coordinate Attention Mechanism

“…Currently, target detection based on deep learning can be categorized into the following two types: two-stage detection algorithms and single-stage detection algorithms. Most of the two-stage detection algorithms rely on the region candidate network to generate candidate frames, and feature extraction of the candidate frame target is carried out by a convolutional neural network [ 8 ]. For example, for a traditional deep learning network in which the feature information transfer process lacks interdependence, Ke et al [ 9 ] proposed a dense attention network structure through the introduction of dense connections as well as an attention module that enhances the detection ability of the model.…”

Multi-Sensors System and Deep Learning Models for Object Tracking

“…Wang et al [ 6 ] utilized radar detections to guide object search in images, while Yu et al [ 7 ] presented a high-level fusion of camera and radar sensors, leveraging deep learning for object detection and Kalman filtering for tracking. Although recent research tends to favor the elimination of radar sensors in favor of relying solely on camera sensors for advanced and autonomous driving functions, as mentioned by the authors in their review [ 8 ], it is important to note that camera sensors still have significant limitations, particularly in the distance and velocity estimation. To address these limitations and ensure better precision and completeness of detections, the integration of range sensors remains necessary.…”