“Looking at the Right Stuff” – Guided Semantic-Gaze for Autonomous Driving


In recent years, predicting driver’s focus of attention has been a very active area of research in the autonomous driving community. Unfortunately, existing state-of-the-art techniques achieve this by relying only on human gaze information, thereby ignoring scene semantics. We propose a novel Semantics Augmented GazE (SAGE) detection approach that captures driving specific contextual information, in addition to the raw gaze. Such a combined attention mechanism serves as a powerful tool to focus on the relevant regions in an image frame in order to make driving both safe and efficient. Using this, we design a complete saliency prediction framework – SAGE-Net, which modifies the initial prediction from SAGE by taking into account vital aspects such as distance to objects (depth), ego vehicle speed, and pedestrian crossing intent. Exhaustive experiments conducted through four popular saliency algorithms show that on 49/56 (87.5%) cases – considering both the overall dataset and crucial driving scenarios, SAGE outperforms existing techniques without any additional computational overhead during the training process. The augmented dataset along with the relevant code are available as part of the supplementary material.

Continue reading

Efficient Hierarchical Graph-Based Segmentation of RGBD Videos


We present an efficient and scalable algorithm for seg- menting 3D RGBD point clouds by combining depth, color, and temporal information using a multistage, hierarchical graph-based approach. Our algorithm processes a moving window over several point clouds to group similar regions over a graph, resulting in an initial over-segmentation. These regions are then merged to yield a dendrogram us- ing agglomerative clustering via a minimum spanning tree algorithm. Bipartite graph matching at a given level of the hierarchical tree yields the final segmentation of the point clouds by maintaining region identities over arbitrarily long periods of time. We show that a multistage segmentation with depth then color yields better results than a linear com- bination of depth and color. Due to its incremental process- ing, our algorithm can process videos of any length and in a streaming pipeline. The algorithm’s ability to produce robust, efficient segmentation is demonstrated with numer- ous experimental results on challenging sequences from our own as well as public RGBD data sets.Continue reading