Pramod Kumar Swami

TL;DR: Methods to reduce the complexity of convolutional neural networks (CNN) include a method to quickly and easily sparsify a given network and how an inference engine can be designed to take advantage of the sparsity.

TL;DR: This paper introduces a high performance front camera ADAS based on a small area, low power System-on-Chip (SoC) solution from Texas Instruments called TDA3x and introduces key programming concepts related to heterogeneous programmable compute cores in the SoC and the software framework to use those cores to develop the front camera solutions.

TL;DR: In this paper, several techniques aimed at reducing computational complexity when encoding uses bi-predictively encoded frames (B-frames) are implemented in a video encoder, such as using B-frames as reference frames for encoding P-frames and other B-frame.

TL;DR: This paper illustrates mapping of different algorithms such as SV, LDW, Object detection (OD), Structure From Motion (SFM) and Camera-Monitor Systems (CMS) to the TDA3x device, thereby demonstrating its compute capabilities, showing that TDA2x is an excellent high performance device for ADAS applications.