18416641. EARLY FUSION OF CAMERA AND RADAR FRAMES simplified abstract (QUALCOMM Incorporated)

EARLY FUSION OF CAMERA AND RADAR FRAMES

Organization Name

QUALCOMM Incorporated

Inventor(s)

Radhika Dilip Gowaikar of San Diego CA (US)

Ravi Teja Sukhavasi of Fremont CA (US)

Daniel Hendricus Franciscus Dijkman of Haarlem (NL)

Bence Major of Amsterdam (NL)

Amin Ansari of Kirkland WA (US)

Teck Yian Lim of Urbana IL (US)

Sundar Subramanian of San Diego CA (US)

Xinzhou Wu of San Diego CA (US)

EARLY FUSION OF CAMERA AND RADAR FRAMES - A simplified explanation of the abstract

This abstract first appeared for US patent application 18416641 titled 'EARLY FUSION OF CAMERA AND RADAR FRAMES

The patent application describes techniques for combining camera and radar frames to detect objects in various spatial domains.

• An on-board computer of a host vehicle processes camera frames and radar frames to extract features.
• The computer converts the extracted features to a common spatial domain for fusion.
• By concatenating the radar and camera feature maps, a concatenated feature map is generated for object detection.

Potential Applications: - Advanced driver assistance systems (ADAS) - Autonomous vehicles - Traffic monitoring and management systems

Problems Solved: - Enhanced object detection accuracy - Improved situational awareness for vehicles - Integration of multiple sensor data for comprehensive analysis

Benefits: - Increased safety on the roads - Better decision-making for autonomous vehicles - Enhanced overall driving experience

Commercial Applications: Title: "Integrated Sensor Fusion Technology for Enhanced Object Detection in Vehicles" This technology can be utilized by automotive manufacturers, tech companies developing autonomous vehicles, and companies in the transportation industry for improving safety and efficiency.

Questions about Integrated Sensor Fusion Technology: 1. How does this technology improve object detection compared to traditional methods? 2. What are the key advantages of combining camera and radar frames for object detection?

Original Abstract Submitted

Disclosed are techniques for fusing camera and radar frames to perform object detection in one or more spatial domains. In an aspect, an on-board computer of a host vehicle receives, from a camera sensor of the host vehicle, a plurality of camera frames, receives, from a radar sensor of the host vehicle, a plurality of radar frames, performs a camera feature extraction process on a first camera frame of the plurality of camera frames to generate a first camera feature map, performs a radar feature extraction process on a first radar frame of the plurality of radar frames to generate a first radar feature map, converts the first camera feature map and/or the first radar feature map to a common spatial domain, and concatenates the first radar feature map and the first camera feature map to generate a first concatenated feature map in the common spatial domain.