Graduate Seminar

Graduate Seminar

Ilya Tcenov


Viterbi Faculty of Electrical Engineering, Technion

Error Prediction for Adaptive Depth Sampling

Autonomous systems require extensive and accurate information regarding the surrounding environment. Efficient data gathering is a fundamental infrastructure for correct decision making of the system, e.g. in navigation and obstacle avoidance. Today, most autonomous systems are equipped with various sensing systems. Although visual stereo systems can be used for depth sensing, their accuracy sharply deteriorates with distance. Moreover, they are vulnerable to camouflaged objects (of low contrast compared to the background), as well as to poor weather conditions. Light Detection and Ranging (LiDAR) sensors are widely used for depth sensing. They are based on active infra-red illumination, and therefore are more robust compared to stereo methods. However, LiDARs sample depth very sparsely, due to system and power constraints. This requires additional post-processing algorithms in order to generate dense depth estimations of the scene. Almost all previous studies focused on the depth completion task, assuming a given fixed sampling pattern. Our goal is to investigate ways to improve the sampling pattern in order to considerably enhance the reconstruction accuracy. Achieving accurate depth maps with fewer samples can result in increased frame-rate, or reduced sensor price. Recent technological developments, based on solid state phased-arrays and MEMS, enable LiDARs to steer the illumination, allowing flexibility in the sampling pattern. Initial studies dealing with flexible patterns do not work well under low sampling budgets. Our preliminary results indicate that RGB camera guidance can significantly improve the LiDAR sampling pattern. Previous work in our group, initiated by Wolff et al., showed the feasibility of such an approach. We present a new framework for image-guided depth sampling that is aimed to reduce depth reconstruction error by generating sampling patterns based on camera imagery. Master’s thesis work supervised by Prof. Guy Gilboa. Zoom link:

Date: Wed 10 Mar 2021

Start Time: 15:00

End Time: 16:00

Zoom meeting | Electrical Eng. Building