General Moving Object Localization from a Single Flying Camera

Abstract

Object localization is an important task in the visual surveillance of scenes, and it has important applications in locating personnel and/or equipment in large open spaces such as a farm or a mine. Traditionally, object localization can be performed using the technique of stereo vision: using two fixed cameras for a moving object, or using a single moving camera for a stationary object. This research addresses the problem of determining the location of a moving object using only a single moving camera, and it does not make use of any prior information on the type of object nor the size of the object. Our technique makes use of a single camera mounted on a quadrotor drone, which flies in a specific pattern relative to the object in order to remove the depth ambiguity associated with their relative motion. In our previous work, we showed that with three images, we can recover the location of an object moving parallel to the direction of motion of the camera. In this research, we find that with four images, we can recover the location of an object moving linearly in an arbitrary direction. We evaluated our algorithm on over 70 image sequences of objects moving in various directions, and the results showed a much smaller depth error rate (less than 8.0% typically) than other state-of-the-art algorithms.

Perspectives of RealSense and ZED Depth Sensors for Robotic Vision Applications

“…These are principal features related to all depth cameras since the lenses, aperture, and light significantly affect the image quality of any camera, not only the depth camera. These features enable high-quality depth images to be obtained, upon which promising robotic vision applications can be developed [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57][58][59]. According to the Stereolabs [16], the main features of ZED cameras are listed in Table 2.…”

“…Up to now, 3D depth cameras have been very expensive, and their utilization has been complex and burdensome from a hardware standpoint. Nowadays, thanks to technical progress, the price of 3D depth sensors that can measure image depth is considerably affordable and their use much simpler [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55][56][57][58][59].…”

Painting Path Planning for a Painting Robot with a RealSense Depth Sensor

“…C2d(x, y) = C(i * ), Z2d(x, y) = X(i * ), [44]. This step uses the cluster method and k-dimensional tree search method to separate clusters [45][46][47][48]. K-d trees are very useful for range and nearest neighbor searches, which are the best for separating possible regions.…”