DSFEC: Efficient and Deployable Deep Radar Object Detection
This work addresses the challenge of efficient radar object detection for edge computing, though it is incremental with specific optimizations.
The paper tackled the problem of deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi by proposing DSFEC models that improve efficiency and deployability, resulting in up to a 14.6% performance improvement and a 78.5% reduction in GFLOPs, with a 74.5% reduction in runtime on the Raspberry Pi.
Deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi poses significant challenges due to the large size of the model and the limited computational power and the memory of the Pi. In this work, we explore the efficiency of Depthwise Separable Convolutions in radar object detection networks and integrate them into our model. Additionally, we introduce a novel Feature Enhancement and Compression (FEC) module to the PointPillars feature encoder to further improve the model performance. With these innovations, we propose the DSFEC-L model and its two versions, which outperform the baseline (23.9 mAP of Car class, 20.72 GFLOPs) on nuScenes dataset: 1). An efficient DSFEC-M model with a 14.6% performance improvement and a 60% reduction in GFLOPs. 2). A deployable DSFEC-S model with a 3.76% performance improvement and a remarkable 78.5% reduction in GFLOPs. Despite marginal performance gains, our deployable model achieves an impressive 74.5% reduction in runtime on the Raspberry Pi compared to the baseline.