Road Mapping In LiDAR Images Using A Joint-Task Dense Dilated Convolutions Merging Network
This work addresses the challenge of road mapping for timber transport in forestry, but it is incremental as it builds on existing deep learning approaches with specific architectural and training improvements.
The paper tackles the problem of accurately mapping roads in LiDAR images for the forest industry by proposing a Dense Dilated Convolutions Merging Network (DDCM-Net) with joint-task learning, achieving better performance with fewer parameters and higher computational efficiency than previous state-of-the-art methods.
It is important, but challenging, for the forest industry to accurately map roads which are used for timber transport by trucks. In this work, we propose a Dense Dilated Convolutions Merging Network (DDCM-Net) to detect these roads in lidar images. The DDCM-Net can effectively recognize multi-scale and complex shaped roads with similar texture and colors, and also is shown to have superior performance over existing methods. To further improve its ability to accurately infer categories of roads, we propose the use of a joint-task learning strategy that utilizes two auxiliary output branches, i.e, multi-class classification and binary segmentation, joined with the main output of full-class segmentation. This pushes the network towards learning more robust representations that are expected to boost the ultimate performance of the main task. In addition, we introduce an iterative-random-weighting method to automatically weigh the joint losses for auxiliary tasks. This can avoid the difficult and expensive process of tuning the weights of each task's loss by hand. The experiments demonstrate that our proposed joint-task DDCM-Net can achieve better performance with fewer parameters and higher computational efficiency than previous state-of-the-art approaches.