Research Publications
All | |
| Narrow your search | 260 result(s) |
By Type
By Year By Research Group | LPBoost seemingly should have better generalization capability than AdaBoost according to the margin theory because LPBoost optimizes the minimum margin directly. Thus far, however, there is no empirical comparison and theoretical explanation of ... This paper presents a preliminary study of the impact of errors in traffic state estimation on traffic signal control performance. We establish numerical relationships to quantify the impact of estimation error, where the impact is measured by vehicle ... CCTV surveillance systems have long been used for public safety. However, the expensive human monitoring of the system due to the huge amount of cameras installed impedes proactive security service to deter crimes. Although automatic faces recognition has... This paper proposes a novel kernel similarity modeling of texture pattern flow (KSM-TPF) for background modeling and motion detection in complex and dynamic environments. The texture pattern flow encodes the binary pattern changes in both spatial and ... This paper proposes a novel computational framework of saliency detection, which jointly models saliency map and proto-objects in images. The proto-objects are detected in salient regions using latent topic model with multi-segmentation. Meanwhile the ... Abstract—Real-time object detection has many applications in video surveillance, teleconference and multimedia retrieval etc. Since Viola and Jones [1] proposed the first real-time AdaBoost based face detection system, much effort has been spent on ... The ability to efficiently and accurately detect predefined objects is very crucial in many vision applications. Recently, offline object detectors have shown a tremendous success. However, one major drawback of offline techniques is that a complete ... For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such ... |