• Corpus ID: 237048428

Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking

  title={Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking},
  author={Gaoang Wang and Renshu Gu and Zuozhu Liu and Weijie Hu and Mingli Song and Jenq-Neng Hwang},
Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motionbased trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging… 

Figures and Tables from this paper


Long-Term Tracking With Deep Tracklet Association
This paper introduces an iterative clustering method that generates more tracklets while maintaining high confidence and proposes a deep association method for tracklet association, which shows robust performance on avoiding internal identity switch.
Multi-Camera Tracking of Vehicles based on Deep Features Re-ID and Trajectory-Based Camera Link Models
An MCT system, which combines single- camera tracking (SCT) and inter-camera tracking (ICT) which includes trajectory-based camera link model and deep feature reidentification and is evaluated on CVPR AI City Challenge 2019 City Flow dataset, achieving IDF1 70.59%, which outperforms competing methods.
The Way They Move: Tracking Multiple Targets with Similar Appearance
We introduce a computationally efficient algorithm for multi-object tracking by detection that addresses four main challenges: appearance similarity among targets, missing data due to targets being
Single-Camera and Inter-Camera Vehicle Tracking and 3D Speed Estimation Based on Fusion of Visual and Semantic Features
A histogram-based adaptive appearance model is introduced to learn long-term history of visual features for each vehicle target and evolutionary optimization is applied to camera calibration for reliable 3D speed estimation.
Multiple Object Tracking With Attention to Appearance, Structure, Motion and Size
This work proposes a method to address MOT by defining a dissimilarity measure based on object motion, appearance, structure, and size, which can achieve state-of-the-art results in both benchmarks.
How to Train Your Deep Multi-Object Tracker
A differentiable proxy of MOTA and MOTP is proposed, which is combined in a loss function suitable for end-to-end training of deep multi-object trackers and establishes a new state of the art on the MOTChallenge benchmark.
FGAGT: Flow-Guided Adaptive Graph Tracking
This article proposes the FGAGT tracker, which reaches the level of state-of-the-art, where the MOTA index exceeds FairMOT by 2.5 points, and CenterTrack by 8.4 points on the MOT17 dataset.
Online Multi-object Tracking via Structural Constraint Event Aggregation
A new data association method is proposed that effectively exploits structural motion constraints in the presence of large camera motion and a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT.
Robust Online Multi-object Tracking Based on Tracklet Confidence and Online Discriminative Appearance Learning
This paper proposes a robust online multi-object tracking method that can handle frequent occlusion by clutter or other objects, and proposes a novel online learning method using an incremental linear discriminant analysis for discriminating the appearances of objects.
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
A concise end-to-end model TubeTK which only needs one step training by introducing the "bounding-tube" to indicate temporal-spatial locations of objects in a short video clip is proposed which achieves state-of-the-art performances even if it adopts no ready-made detection results.