Modality-Buffet for Real-Time Object Detection

Real-time object detection in videos using lightweight hardware is a crucial component of many robotic tasks. Detectors using different modalities and with varying computational complexities offer different trade-offs. One option is to have a very lightweight model that can predict from all modalities at once for each frame. However, in some situations (e. g. , in static scenes) it might be better to have a more complex but more accurate model and to extrapolate from previous predictions for the frames coming in at processing time. We formulate this task as a sequential decision making problem and use reinforcement learning (RL) to generate a policy that decides from the RGB input which detector out of a portfolio of different object detectors to take for the next prediction. The objective of the RL agent is to maximize the accuracy of the predictions per image. We evaluate the approach on the Waymo Open Dataset and show that it exceeds the performance of each single detector.

Authors

• Nicolai Dorka
• Johannes Meyer
• Wolfram Burgard

Keywords

• Computational modeling
• Detectors
• Object detection
• Predictive models
• Real-time systems
• Task analysis
• Portfolios
• Real-time Object Detection
• Accuracy Of Model
• Reinforcement Learning Agent
• Static Scenes
• Detection In Videos
• Prediction Model
• Training Set
• Intersection Over Union
• Bounding Box
• RGB Images
• Inference Time
• Policy Learning
• Reinforcement Learning Algorithm
• Faster R-CNN
• Lidar Data
• Feature Pyramid Network
• Reward Signal
• LiDAR Scans
• Replay Buffer
• Intersection Over Union Threshold
• Object Detection Problem
• Average Precision Score
• State St
• Future Frames
• 3D Bounding Box
• Rainbow
• Fast Implementation
• Average Precision
• Heuristic