Semantic Segmentation of Road Profiles for Efficient Sensing in Autonomous Driving

Abstract

In vision-based autonomous driving, understanding spatial layout of road and traffic is required at each moment. This involves the detection of road, vehicle, pedestrian, etc. in images. In driving video, the spatial positions of various patterns are further tracked for their motion. This spatial-to-temporal approach inherently demands a large computational resource. In this work, however, we take a temporal-to-spatial approach to cope with fast moving vehicles in autonomous navigation. We sample one-pixel line at each frame in driving video, and the temporal congregation of lines from consecutive frames forms a road profile image. The temporal connection of lines also provides layout information of road and surrounding environment. This method reduces the processing data to a fraction of video in order to catch up vehicle moving speed. The key issue now is to know different regions in the road profile; the road profile is divided in real time to road, roadside, lane mark, vehicle, etc. as well as motion events such as stopping and turning of ego-vehicle. We show in this paper that the road profile can be learned through Semantic Segmentation. We use RGB-F images of the road profile to implement Semantic Segmentation to grasp both individual regions and their spatial relations on road effectively. We have tested our method on naturalistic driving video and the results are promising.

Autonomous Vehicles Perception (AVP) Using Deep Learning: Modeling, Assessment, and Challenges

“…The proposed method was validated on the 'Cityscape' dataset and resulted in a high performance, particularly on people and bicycles of different shapes. In [10], the authors tackled the need for a large computational resource for spatialto-temporal approaches implemented in autonomous vehicles when tracking the various patterns of spatial positions for their motion. They proposed a temporal-to-spatial approach to cope with the vehicle's speed in autonomous navigation by sampling a 1-pixel line at each frame in the video.…”

“…Another dataset for semantic segmentation in [7], [10], and [11] is The Cambridge -driving Labeled Video Database (CamVid) [41]. It provides per-pixel semantic segmentation of over 700 images, 367 training, 101 validation, and 233 test images of 32 semantic classes.…”

“…Intersection Over Union (IoU) matric, also known as Jaccard Index, is widely used to evaluate semantic segmentation and object detection models [10]. It computes the percent overlap between the ground truth bounding box (in object detection) or the target mask (in semantic segmentation) and the prediction output.…”

“…VOLUME 10,2022 This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.…”

Landslide Detection Using a Saliency Feature Enhancement Technique From LiDAR-Derived DEM and Orthophotos

“…The mIOU=1 indicates a perfect prediction and greater than 0.5 is normally considered a "good" prediction [66]. mIOU was computed using (7) [67].…”