End to end collision avoidance based on optical flow and neural networks

2019/11/06 by Jan Blumenkamp, Blumenkamp, Jan
Agricultural and Biological Sciences · Computer Science · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques #Leaf Properties and Growth Measurement #Machine Learning (cs.LG) #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.1911.08582

openalex publication_date 2019/11/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Optical flow is believed to play an important role in the agile flight of birds and insects. Even though it is a very simple concept, it is rarely used in computer vision for collision avoidance. This work implements a neural network based collision avoidance which was deployed and evaluated on a solely for this purpose refitted car.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The interpretation of a moving retinal image

Related

• A Visual Neural Network for Robust Collision Perception in Vehicle Driving Scenarios
• Reactive Collision Avoidance using Evolutionary Neural Networks
• A neural model of the locust visual system for detection of object approaches with real-world scenes
• N-MPC for Deep Neural Network-Based Collision Avoidance exploiting Depth Images
• Optical Flow Based Motion Detection for Autonomous Driving