Camera and LiDAR analysis for 3D object detection in foggy weather conditions

Abstract

Today, the popularity of self-driving cars is growing at an exponential rate and is starting to creep onto the roads of developing countries. For autonomous vehicles to function, one of the essential features that needs to be developed is the ability to perceive their surroundings. To do this, sensors such as cameras, LiDAR, or radar are integrated to collect raw data. The objective of this paper is to evaluate a fusion solution of cameras and LiDARs (4 and 64 beams) for 3D object detection in foggy weather conditions. The data from the two input sensors are fused and an analysis of the contribution of each sensor on its own is then performed. In our analysis, we calculate average precision using the popular KITTI dataset, on which we have applied different intensities of fog (on a dataset we have called Multifog KITTI). The main results observed are as follows. Performances with stereo camera and 4 or 64 beams LiDAR are high (90.15%, 89.26%). Performance of the 4 beams LiDAR alone decreases sharply in foggy weather conditions (13.43%). Performance when using only a camera-based model remains quite high (89.36%). In conclusion, stereo cameras on their own are capable of detecting 3D objects in foggy weather with high accuracy and their performance slightly improves when used in conjunction with LIDAR sensors.

3D Object Detection for Self-Driving Cars Using Video and LiDAR: An Ablation Study

“…The quantitative results showed that the detection performance drops moderately with each component disabled (stereo camera or LiDAR) or by modifying the number of LiDAR beams, and the full model works best. Moreover, this fusion approach was found to be very useful in detecting 3D objects in foggy weather conditions [ 54 ]…”

Qualification of the PAVIN Fog and Rain Platform and Its Digital Twin for the Evaluation of a Pedestrian Detector in Fog

“…Similarly, the environment, disturbing objects, and occlusions can influence the detection. Beyond these geometric issues, weather conditions also have strong impacts, e.g., illumination, camera glare [4,5], fog [6][7][8][9][10], rain [7,10,11], and snow [8]. Interest in this issue is recent in the field of autonomous vehicles and is the subject of numerous studies [12][13][14], but at present, the works listed in the literature only present particular cases and not a global solution.…”