We propose an RGB-D single-object tracker, built upon the extremely fast RGB-only KCF tracker that is able to exploit depth information to handle scale changes, occlusions, and shape changes. Despite the computational demands of the extra functionalities, we still achieve realtime performance rates of 35-43 fps in MATLAB and 187 fps in our C?? implementation. Our proposed method includes fast depth-based target object segmentation that enables, (1) efficient scale change handling within the KCF core functionality in the Fourier domain, (2) the detection of occlusions by temporal analysis of the target's depth distribution, and (3) the estimation of a target's change of shape through the temporal evolution of its segmented silhouette allows. Finally, we provide an in-depth analysis of the factors affecting the throughput and precision of our proposed tracker and perform extensive comparative analysis. Both the MATLAB and C?? versions of our software are available in the public domain.
Video surveillance systems are now widely deployed to improve our lives by enhancing safety, security, health monitoring and business intelligence. This has motivated extensive research into automated video analysis. Nevertheless, there is a gap between the focus of contemporary research, and the needs of end users of video surveillance systems. Many existing benchmarks and methodologies focus on narrowly defined problems in detection, tracking, re-identification or recognition. In contrast, end users face higher-level problems such as long-term monitoring of identities in order to build a picture of a person's activity across the course of a day, producing usage statistics of a particular area of space, and that these capabilities should be robust to challenges such as change of clothing. To achieve this effectively requires less widely studied capabilities such as spatio-temporal reasoning about people identities and locations within a space partially observed by multiple cameras over an extended time period. To bridge this gap between research and required capabilities, we propose a new dataset LIMA that encompasses the challenges of monitoring a typical home / office environment. LIMA contains 4.5 hours of RGB-D video from three cameras monitoring a four room house. To reflect the challenges of a realistic practical application, the dataset includes clothes changes and visitors to ensure the global reasoning is a realistic open-set problem. In addition to raw data, we provide identity annotation for benchmarking, and tracking results from a contemporary RGB-D tracker-thus allowing focus on the higher level monitoring problems.
The Piper Alpha Public Inquiry heard 13 months of evidence. In that time much about what happened on the day of the disaster became known. It also became clear that inadequacies existed in accepted industry safety practice. Lord Cullen, the Judge in charge of the Inquiry, reported a considerable part of this evidence in his recent report and recommendations. Conoco wanted to ensure it learned all it could from the Inquiry. It wanted to learn not only from the report, but anything else it could learn directly from the evidence itself. It wanted to check its own safety systems against the evidence. Finally, to enhance safety awareness generally within the company, it wanted to make known to its employees as much as possible about the evidence and the safety lessons it provided. INTRODUCTION Immediately following the piper disaster, Conoco - like most companies operating in the UK - thoroughly examined all aspects of its safety policy and practices. TO do this, a number of teams were formed incorporating personnel from production, safety and engineering. Each team reviewed an area for possible safety improvements to its North Sea facilities. These are some of their recommendations:Locate pipeline emergency shut down valves in a safe position. Generally, this meant positioning the valve in the cellar deck close to the top of the riser. Then appropriately protecting the valve from all identifiable sources of explosion and fire.Relocate Viking 'A' and 'B' accommodation to a dedicated support structure. Conoco has two separate multi-platform complexes close together. Quarters on each are on platforms with import pipeline risers. As the water is shallow (100ft) it is realistic to provide a dedicated accommodation support structure. Rather than built two such dedicated units, a single unit at one complex is to be built, with the second complex then unmanned and remotely operated from the first.Mark out escape ways to be visible in dark smoky conditions. Originally the escape routes were full yellow painted roadways, but because these proved slippery in wet conditions black anti-slip tiles were fitted. Yellow photoluminescent discs spaced at regular intervals have now been applied along these routes.Supply grab bags in all bedrooms. All crew members now have by their beds a bright yellow holdall which contains all their survival equipment: survival suit, life jacket, smoke hood, and leather gloves. So in an emergency people can quickly grab their bags as they hurry to their muster station, with less chance of any essential item being forgotten or difficult to find - particularly in dark or smoky conditions.Provide torches in all bedrooms.Mark exits from accommodation. Exit doors have always been illuminated. Now, in addition, all internal walls (at floor level), door frames and door handles are outlined with photoluminescent tape to improve their visibility even in thick smoke.Fit guards on subsea fire pump suction caissons. Prior to fitting these cages it was common industry practice to isolate the fire when divers were working close to the pump suction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.