The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Boosting-based object detection has received significant attention recently. In this paper, we propose totally corrective asymmetric boosting algorithms for real-time object detection. Our algorithms differ from Viola and Jones' detection framework in two ways. Firstly, our boosting algorithms explicitly optimize asymmetric loss of objectives, while AdaBoost used by Viola and Jones optimizes a symmetric...
Correcting infrared camera distortion is necessary in target tracking and object recognition system. The existent FPGA algorithm didn't utilize sufficiently the advantage of the parallel processing and leaded to the results that a great deal of the system resources were consumed and the running speed was slowed down. The paper analyzed the existing problems such as serial structure in other algorithms,...
Efficient visual object detection is of central interest in computer vision and pattern recognition due to its wide ranges of applications. Viola and Jones' detector has become a de facto framework [1]. In this work, we propose a new method to design a cascade of boosted classifiers for fast object detection, which combines linear asymmetric classification (LAC) into the recent multi-exit cascade...
The traditional fixed bandwidth Mean-Shift Tracking algorithm can not have an effective tracking for any changes in targets. Based on the current methods, the tracking are particularly effective on gradually increase or decrease in size, there has no Mean-shift Tracking fit the size in any change. On the basic of this, we propose a combination of traditional algorithm bandwidth adaptive algorithm...
This paper is aimed to propose a new method for the discerning of point moving targets' tracks to improve the current search strategies, which can not make full use of the entire trace information based on the domain of current point target location. By using the PRI search of least-square trace prediction, we establish a trace-fitting model based on probability and statistics. By setting the predicted...
This paper discusses the relationship between Danger Theory and image object detection, and interprets the produce of the image object detection using Danger Theory. In the paper, the image object detection is mimiced as the produce that biology immune system detects danger antigens, where the interested object are regarded as ldquodanger antigensrdquo and object detectors are regarded as antigen...
In this paper, an integrated algorithm to detect bridge objects over rivers was introduced for satellite imagery interpretation. It is composed of two steps: first, segment the river from complex background using data driven strategy; second, detect the bridges in the shrink searching area using knowledge driven strategy. Considering the ubiety of the bridges and the surroundings, this paper focused...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.