Sorry, you need to enable JavaScript to visit this website.

Deep Learning-based Obstacle Detection and Depth Estimation

Citation Author(s):
Wei-Yu Lin, Dong-Lin Li, and Jen-Hui Chuang
Submitted by:
Yi-Yu Hsieh
Last updated:
19 September 2019 - 9:32pm
Document Type:
Presentation Slides
Document Year:
2019
Event:
Presenters:
Jen-Hui Chuang
Paper Code:
3455
 

This paper proposed a modified YOLOv3 which has an extra object depth prediction module for obstacle detection and avoidance. We use a pre-processed KITTI dataset to train the proposed, unified model for (i) object detection and (ii) depth prediction and use the AirSim flight simulator to generate synthetic aerial images to verify that our model can be applied in different data domains. Experimental results show that the proposed model compares favorably with other depth map prediction methods in terms of accuracy in the prediction of object depth for pre-processed KITTI dataset, while the unified approach can actually improve both (i) and (ii) at the same time.

up
0 users have voted: