Event-Based Moving Object Detection and Tracking

By A. Mitrokhin, Cornelia Fermüller, Chethan Parameshwara, Yiannis Aloimonos. IEEE/RJS International Conference on Intelligent RObots and Systems, 2018

375 citations recorded by the source corpus.

Event-based vision sensors, such as the Dynamic Vision Sensor (DVS), are ideally suited for real-time motion analysis. The unique properties encompassed in the readings of such sensors provide high temporal resolution, superior sensitivity to light and low latency. These properties provide the grounds to estimate motion efficiently and reliably in the most sophisticated scenarios, but these advantages come at a price - modern event-based vision sensors have extremely low resolution, produce a lot of noise and require the development of novel algorithms to handle the asynchronous event stream. This paper presents a new, efficient approach to object tracking with asynchronous cameras. We present a novel event stream representation which enables us to utilize information about the dynamic (temporal)component of the event stream. The 3D geometry of the event stream is approximated with a parametric model to motion-compensate for the camera (without feature tracking or explicit optical flow computation), and then moving objects that don't conform to the model are detected in an iterative process. We demonstrate our framework on the task of independent motion detection and tracking, where we use the temporal model inconsistencies to locate differently moving objects in challenging situations of very fast motion.

Subfields: Bioengineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/4d05394e096ce203524d3085c296b17eb0a74b6a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Bioengineering

In Electrical and Electronic Engineering

Citations in the corpus

Dynamic obstacle avoidance for quadrotors with event cameras (2020, methodology): “While the original approach (23) uses a fixed threshold to distinguish between ego-motion generated events and those generated by a moving object, we instead use a linear function that depends on the angular velocity’s magnitude, i.”
Low-latency automotive vision with event cameras (2024, positive): “These approaches treat events as spatio-temporal point clouds 75 , submanifolds 36 or graphs 31,32,43,76 and process them with specialized neural networks.”
Event-Based Vision: A Survey (2019, background): “Segmentation has been addressed by [116], [138], [139] under mild assumptions leveraging the idea of motion-compensated event images [111] (Section 3).”
Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion (2018, background): “[13], who use a loss which minimizes the sum of squares of the average timestamp at each pixel.”