US 11,447,151 B2 · Object detection under rainy conditions for autonomous systems

Abstract

Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects, most notably pedestrians and other nearby cars, to assist the corresponding vehicles maneuver safely in their environment. However, the performance of object detection methods is anticipated to degrade under challenging rainy conditions. Nevertheless, and despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous systems. This disclosure analyzes this problem space and presents an improved system for detecting objects under rainy conditions.

Claims10

Dependent claims

A system for detecting objects in a scene under rainy weather conditions, comprising:

a camera configured to capture image data of the scene;
a neural network configured to receive the image data from the camera and operates to classify objects contained in the image data;
multiple sets of weights for use by the neural network, where data with different levels of rain intensity therein is used to generated the multiple sets of weights
a rain sensor;
and
a selector interfaced with the rain sensor and the neural network, wherein the selector loads a given set of weights for use by the neural network based on input from the rain sensor, and the given set of weights corresponds to a level of rain intensity measured by the rain sensor.

3 more elements

Dependencies are inferred from the claim text.

Object detection under rainy conditions for autonomous systems

Life of this patent

Object detection under rainy conditions for autonomous systems

Life of this patent

Abstract

Claims10