Portrait photo retouching is a photo retouching task that emphasizes human-region priority and group-level consistency. The lookup table-based method achieves promising retouching performance by learning image-adaptive weights to combine 3-dimensional lookup tables (3D LUTs) and conducting pixel-to-pixel color transformation. However, this paradigm ignores the local context cues and applies the same transformation to portrait pixels and background pixels when they exhibit the same raw RGB values. In contrast, an expert usually conducts different operations to adjust the color temperatures and tones of portrait regions and background regions. This inspires us to model local context cues to improve the retouching quality explicitly. Firstly, we consider an image patch and predict pixel-adaptive lookup table weights to precisely retouch the center pixel. Secondly, as neighboring pixels exhibit different affinities to the center pixel, we estimate a local attention mask to modulate the influence of neighboring pixels. Thirdly, the quality of the local attention mask can be further improved by applying supervision, which is based on the affinity map calculated by the groundtruth portrait mask. As for group-level consistency, we propose to directly constrain the variance of mean color components in the Lab space. Extensive experiments on PPR10K dataset verify the effectiveness of our method, e.g. on high-resolution photos, the PSNR metric receives over 0.5 gains while the grouplevel consistency metric obtains at least 2.1 decreases.
Because of the special environment and the risk of accident in the coal mine, some of the major problems that concern the people are the safety production, managing and rescuing workers under the mine. To solve these problems, this paper brings out the Underground Personnel Position System with RFID (Radio Frequency Identification technology). RFID is a new wireless communication technology and widely applied in other industry. The technology can be used to automatically identify the information of the workers, locate their positions on time and record their tracks, which can improve the information management level of the coal mine greatly and provide the necessary information for management and rescuing.In addition, GIS is also used to provide a visual window to assist the Position System to make a more convenient management on the workers' location. It is clear that the GISbased Mine Safety Management Information System can absolutely achieve a better impact with the seamless link of spatial data whose format is called SHP and some else property data. And the system can greatly improve the efficiency of the mine safety management. Index Terms-RFID, Position System, coal mine, GIS I. ISSUES RAISED A.Background for the Development of the System Production safety in the underground coal mines has been always a bearing on people's lives and property. People have attached great importance to this issue for a long time and taken a series of measures to continuously strengthen the production safety. Although continuous efforts related to a variety of coal mine safety have been applied, the situation of the coal mine production safety is still not optimistic for various reasons. Particularly, serious accidents due to coal mine safety management and oversight are still occurring. How to change the present out-dated management style in which coal companies manage the workers and materials in the underground mines and how to achieve the modernization and informationization of management has become a concern of all coal mine enterprises. So as to the establishment of disaster prevention and management of electronic information especially the system for life rescue, building the intelligent object position information management system for these enterprises becomes imperative.However, well-known and commonly used traditional positioning system GPS is limited by the target's acquisition for the satellite signal, while the satellite signal is not accessible on the underground floor of the mine. With continuous development of RFID technology, people find a new solution on the issue to the location in the underground coal mine. RFID (Radio Frequency Identification) is a non-contact automatic identification technology. Through the radio frequency signal of RFID, automatic target identification can be carried out quickly as well as tracking goods and data exchange. RFID technology can identify objects in high-speed movement and also identify a number of tags at the same time quickly and conveniently. It does not need any human i...
Pallet pooling system establishes a considerable number of pallet recycling stations throughout the country to recycle and maintain the pallets. The main advantages of the pallet pooling system are greatly improving the logistics efficiency by achieving pallet through transport, reducing the total number of social pallets by renting the pallets and can reduce the cost of the international logistics. RFID (Radio Frequency Identification) is one of the automatic identification technologies. RFID utilizes the non-contact data exchange to identify the object, which has many advantages such as rapid identification, wear-free, out of the environmental impact, long life, etc. RFID has been developing quickly at home and abroad, which has been widely used in many fields such as industrial automation, commercial automation, control and management of transport. In this paper, the author describes how to use RFID technology on pallets for information management in pallet rental system. Firstly, the author introduces orderly what pallet rental system is, why we need to establish pallet rental system, how to establish such a system, why we should make use of RFID technology and how to use RFID technology in the pallet rental information system; Secondly, the author makes an analysis on the overall structure of the system, information flow and business process in the pallet rental system; Finally the author gives an application of pallet rental information system based on RFID.
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.