TCM: A Vision-Based Algorithm for Distinguishing between Stationary and Moving Objects Irrespective of Depth Contrast from a UAS

Abstract

This paper describes an airborne vision system that is capable of determining whether an object is moving or stationary in an outdoor environment. The proposed method, coined the Triangle Closure Method (TCM), achieves this goal by computing the aircraft's egomotion and combining it with information about the directions connecting the object and the UAS, and the expansion of the object in the image. TCM discriminates between stationary and moving objects with an accuracy rate of up to 96%. The performance of the method is validated in outdoor field tests by implementation in real-time on a quadrotor UAS. We demonstrate that the performance of TCM is better than that of a traditional background subtraction technique, as well as a method that employs the Epipolar Constraint Method. Unlike background subtraction, TCM does not generate false alarms due to parallax when a stationary object is at a distance other than that of the background. It also prevents false negatives when the object is moving along an epipolar constraint. TCM is a reliable and computationally efficient scheme for detecting moving objects, which provides an additional safety layer for autonomous navigation.

Bio-Inspired Principles Applied to the Guidance, Navigation and Control of UAS

“…The performance of the method is validated in outdoor field tests, shown in Figure 15, by implementation in real-time on a quadrotor UAS (An airborne vision system for the detection of moving objects using TCM video available at: https://youtu.be/Hrgf0AiZ214). TCM discriminates between stationary and moving objects with an accuracy of up to 97% [130,131]. The study by [131] additionally compares TCM with that of a traditional background subtraction technique, where the background subtraction method compensates for the motion of the aircraft; this is referred to in [131] as "moving background subtraction".…”

“…TCM discriminates between stationary and moving objects with an accuracy of up to 97% [130,131]. The study by [131] additionally compares TCM with that of a traditional background subtraction technique, where the background subtraction method compensates for the motion of the aircraft; this is referred to in [131] as "moving background subtraction". Unlike that technique, TCM does not generate false alarms that can be caused by parallax when a stationary object is at a different distance to the background.…”

“…We have shown above that moving object detection can be accomplished in a variety of ways, predominantly through the sensing of motion contrast and utilising the epipolar constraint. The methods described in [130,131] are able to robustly distinguish between moving and static objects and overcome some of the limitations of current techniques.…”

Spherical formulation of moving object geometric constraints for monocular fisheye cameras

“…In contrast, we will reformulate the epipolar constraint to natively work on the vectors that constitute the spherical space, without the need for local tangent space or the epipolar projection to 1-D locus in fisheye space. Strydom et al [17] have also proposed a method for the detection of moving objects in spherical coordinates based on the object triangulation. However, their method requires the knowledge of the object shape, which is assumed to not change in time, which brings additional complications that do not pertain to the geometrical treatment.…”

UAS stealth: target pursuit at constant distance using a bio-inspired motion camouflage guidance law

“…• Many monocular vision-based detection algorithms for detecting approaching objects look for expansion (e.g. [26]), which the CDMC method will not generate. • For surveillance tasks that require the use of high optical zoom for detailed inspection, the target distance will remain constant, and thus the optical zoom setting can remain unchanged while the aircraft is achieving motion camouflage.…”