|
Autonomous vehicles
Robotics
Surveillance and security
Abstract
USC researchers bring advanced retinal computations to image sensors with Integrated Retinal Functionality in Image Sensors (IRIS). By leveraging recent advancements in inner retinal circuits, IRIS goes beyond basic luminance adaptation and change detection. It mimics the feature-selective...
|
|
Integrated circuits
Abstract
USC inventors propose an analog optical interconnect between the CMOS image sensor and the memory/processor that enables significant bandwidth reduction and promotes energy efficiency. This method would both remove the need for for ADCs between transceiver nodes and allow for analog in-memory/pixel computation, resulting...
|
|
Autonomous driving
Surveillance
Object detection; Object tracking; Anomaly detection
Abstract
USC researchers have developed an asynchronous processing-in-pixel-in-memory (P2M) paradigm that improves energy efficiency and decreases processing requirements and data transfer differences without sacrificing significant accuracy. The P2M paradigm consumes...
|