JLA, or Joint Learning Architecture, is an approach for multiple object tracking and trajectory forecasting. It jointly trains a tracking and trajectory forecasting model, and the trajectory forecasts are used for short-term motion estimates in lieu of linear motion prediction methods such as the Kalman filter. It uses a FairMOT model as the base model because this architecture already performs detection and tracking. A forecasting branch is added to the network and is trained end-to-end. FairMOT consist of a backbone network utilizing Deep Layer Aggregation, an object detection head, and a reID head.
Source: Joint Learning Architecture for Multiple Object Tracking and Trajectory ForecastingPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
motion prediction | 1 | 25.00% |
Multiple Object Tracking | 1 | 25.00% |
Object Tracking | 1 | 25.00% |
Trajectory Forecasting | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |