A Lightweight Online Multiple Object Vehicle Tracking Method

In this paper, multiple-object vehicle tracking system by affinity matching using min-cost linear cost assignment is proposed. This tracking system is targeted to scene recordings acquired from cameras mounted on a moving ego vehicle. Vehicle tracking on the road scene and images acquired from moving ego vehicle's camera amplifies the problem of greater bounding box geometry change in comparison with other low speed tracking applications such as traditional pedestrian tracking. This perturbation occurs in many tracking scenarios such as when a high speed object is approaching from an opposing lane. Since autonomous driving algorithms need to use the processing resources in an efficient manner even while satisfying the requirements of computationally complex tasks like localization, object detection, occupancy grid update, sensor-fusion and trajectory planning, our study is particularly focused on the development and benchmarking of an computationally lightweight online multiple object tracking model. To test and evaluate our model, we use KITTI Object Tracking - Car Benchmark dataset and our model statistical metric values are comparably higher; our model outperforms the state-of-the-art methods on ML and MT and places second on MOTA and MOTP metric evaluations, and processing time is 6 to 20 times faster compared to other methods.