Ioannis Pitas

Abstract: This special issue covering autonomous driving is presented in two parts: Part 1—Sensing and Perception was published in the July 2020 issue of IEEE Signal Processing Magazine and this issue, Part 2—Learning and Cognition. Learning and cognition models and, in particular, deep learning-based models are at the core of autonomous vehicles and automated driving. Autonomous driving and, more generally, automated driving are receiving increasing attention, and significant resources are being deployed to enable safe, reliable, and efficient automated mobility in real-world environments.

TL;DR: The method generates the appropriate data, as specified in the MPEG-4 standard, such as the face definition parameters (FDPs), the face animation parameters ( FAPs) and the facial animation table (FAT) from an animated face model in Maya.

TL;DR: Parallel algorithms on barrel shifter computers for a broad class of 1-D and 2-D signal operators are presented in this paper and require a significantly smaller number of comparisons/computations per output point than the conventional ones.

TL;DR: Experimental results showed that the proposed method outperforms state of the art methods on facial images extracted from stereo movies and on the UCF11 action recognition database.

TL;DR: The proposed object tracking scheme was tested on hand sequences created for testing gesture recognition algorithms under difficult illumination conditions and found to perform better than a scheme based on the Kullback-Leibler distance and a schemebased on gradient information.