Expandable YOLO: 3D Object Detection from RGB-D Images
This work addresses real-time object detection for automated driving by reducing network size, though it is incremental.
The paper tackles 3D object detection from RGB-D images by extending YOLOv3 to output in the depth direction and introducing 3D IoU for accuracy, achieving a processing speed of 44.35 fps.
This paper aims at constructing a light-weight object detector that inputs a depth and a color image from a stereo camera. Specifically, by extending the network architecture of YOLOv3 to 3D in the middle, it is possible to output in the depth direction. In addition, Intersection over Uninon (IoU) in 3D space is introduced to confirm the accuracy of region extraction results. In the field of deep learning, object detectors that use distance information as input are actively studied for utilizing automated driving. However, the conventional detector has a large network structure, and the real-time property is impaired. The effectiveness of the detector constructed as described above is verified using datasets. As a result of this experiment, the proposed model is able to output 3D bounding boxes and detect people whose part of the body is hidden. Further, the processing speed of the model is 44.35 fps.