Does depth estimation help object detection?
This work addresses the problem of effectively integrating depth data into object detection for computer vision applications, but it is incremental as it builds on existing depth estimation and detection frameworks.
The paper investigates factors affecting object detection performance when using estimated depth, finding that ground-truth depth improves accuracy but estimated depth does not always help. It proposes an early concatenation strategy that achieves higher mAP with fewer parameters than previous methods.
Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color. However, estimated depth does not always yield improvements. Many factors affect the performance of object detection when estimated depth is used. In this paper, we comprehensively investigate these factors with detailed experiments, such as using ground-truth vs. estimated depth, effects of different state-of-the-art depth estimation networks, effects of using different indoor and outdoor RGB-D datasets as training data for depth estimation, and different architectural choices for integrating depth to the base object detector network. We propose an early concatenation strategy of depth, which yields higher mAP than previous works' while using significantly fewer parameters.