# Object Tracking by Detection with Visual and Motion Cues

arXiv: https://arxiv.org/abs/2101.07549 · HTML: https://mlsanity.com/paper/2101.07549/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net](https://mlsanity.com/paper/2012.12395/) (2020)
- [Detect to Track and Track to Detect](https://mlsanity.com/paper/1710.03958/) (2017)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings](https://mlsanity.com/paper/2002.07662/) (2020)

## Built on by (most cited first, 1 of 1)

- [ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation](https://mlsanity.com/paper/2303.16382/) (2023)

## Abstract (arXiv)

Self-driving cars and other autonomous vehicles need to detect and track objects in camera images. We present a simple online tracking algorithm that is based on a constant velocity motion model with a Kalman filter, and an assignment heuristic. The assignment heuristic relies on four metrics: An embedding vector that describes the appearance of objects and can be used to re-identify them, a displacement vector that describes the object movement between two consecutive video frames, the Mahalanobis distance between the Kalman filter states and the new detections, and a class distance. These metrics are combined with a linear SVM, and then the assignment problem is solved by the Hungarian algorithm. We also propose an efficient CNN architecture that estimates these metrics. Our multi-frame model accepts two consecutive video frames which are processed individually in the backbone, and then optical flow is estimated on the resulting feature maps. This allows the network heads to estimate the displacement vectors. We evaluate our approach on the challenging BDD100K tracking dataset. Our multi-frame model achieves a good MOTA value of 39.1% with low localization error of 0.206 in MOTP. Our fast single-frame model achieves an even lower localization error of 0.202 in MOTP, and a MOTA value of 36.8%.