Moving object detection in top-view aerial videos improved by image stacking

Abstract

Abstract. Image stacking is a well-known method that is used to improve the quality of images in video data. A set of consecutive images is aligned by applying image registration and warping. In the resulting image stack, each pixel has redundant information about its intensity value. This redundant information can be used to suppress image noise, resharpen blurry images, or even enhance the spatial image resolution as done in superresolution. Small moving objects in the videos usually get blurred or distorted by image stacking and thus need to be handled explicitly. We use image stacking in an innovative way: image registration is applied to small moving objects only, and image warping blurs the stationary background that surrounds the moving objects. Our video data are coming from a small fixed-wing unmanned aerial vehicle (UAV) that acquires top-view gray-value images of urban scenes. Moving objects are mainly cars but also other vehicles such as motorcycles. The resulting images, after applying our proposed image stacking approach, are used to improve baseline algorithms for vehicle detection and segmentation. We improve precision and recall by up to 0.011, which corresponds to a reduction of the number of false positive and false negative detections by more than 3 per second. Furthermore, we show how our proposed image stacking approach can be implemented efficiently. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Promise of Fully Integrated PET/MRI: Noninvasive Clinical Quantification of Cerebral Glucose Metabolism

“…The petrous region was automatically segmented from the 3D TOF-MRA sequence using an algorithm proposed by Sundar et al (11). A combination of histogram-based quantile thresholding (20) and an automatic seeded regiongrowing algorithm created a mask of carotid vessels. Given that the petrous segment of the ICA was well defined by a distinct morphology (geometric orientation, axis length, and ellipticity), it could be easily extracted from axial slices, yielding the ICA target region (P mask ).…”

Intelligent Traffic Surveillance through Multi-Label Semantic Segmentation and Filter-Based Tracking

“…The methodology presented a two-stage approach i.e., cloud-based image enhancement and edge-based detection which is an efficient and dynamic approach to address each image contrast enhancement requirement separately. The authors of [11] employed an innovative method for image stacking. Only small cars were included in the image registration procedure, and all of the stationary backgrounds near the moving vehicles were blurred using the warping technique.…”