Real-time automatic detection and tracking of moving vehicles in videos acquired by airborne cameras is a challenging problem due to vehicle occlusion, camera movement, and high computational cost. This paper presents an efficient and robust real-time approach for automatic vehicle detection and tracking in aerial videos that employ both detections and tracking features to enhance the final decision. The use of Top-hat and Bottom-hat transformation aided by the morphological operation in the detection phase has been adopted. After detection, background regions are eliminated by motion feature points’ analysis of the obtained object regions using a combined technique between KLT tracker and K-means clustering. Obtained object features are clustered into separate objects based on their motion characteristic. Finally, an efficient connecting algorithm is introduced to assign the vehicle labels with their corresponding cluster trajectories. The proposed method was tested on videos taken in different scenarios. The experimental results showed that the recall, precision, and tracking accuracy of the proposed method were about 95.1 %, 97.5%, and 95.2%, respectively. The method also achieves a fast processing speed. Thus, the proposed approach has superior overall performance compared to newly published approaches.

Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature points motion analysis

RETRACTED: Image quality tendency modeling by fusing multiple visual cues

In recent years, the use of object proposal as a preprocessing step for target detection to improve computational efficiency has become an effective method. Good object proposal methods should have high object detection recall rate and low computational cost, as well as good localization quality and repeatability. However, it is difficult for current advanced algorithms to achieve a good balance in the above performance. For this problem, we propose a class-independent object proposal algorithm BIHL. It combines the advantages of window scoring and superpixel merging, which not only improves the localization quality but also speeds up the computational efficiency. The experimental results on the VOC2007 data set show that when the IOU is 0.5 and 10,000 budget proposals, our method can achieve the highest detection recall and an mean average best overlap of 79.5%, and the computational efficiency is nearly three times faster than the current fastest method. Moreover, our method is the method with the highest average repeatability among the methods that achieve good repeatability to various disturbances.

A High-Performance Object Proposals based on Horizontal High Frequency Signal

BIHL:A Fast and High Performance Object Proposals based on Binarized HL Frequency

In this paper, a moving object detection algorithm is combined with a background estimate and a Bing (Binary Norm Gradient) object is proposed in video surveillance. A simple background estimation method is used to detect rough images of a group of moving foreground objects. The foreground setting in the foreground will estimate another set of candidate object windows, and the target (pedestrian / vehicle) from the intersection area comes from the first two steps. In addition, the time cost is reduced by the estimated area. Experiments on outdoor datasets show that the proposed method can not only achieve high detection rate (DR), but also reduce false alarm rate (FAR) and time cost.

/pdf/retracted-article-moving-object-surveillance-using-object-1t0ae0r711.pdf

RETRACTED ARTICLE: Moving object surveillance using object proposals and background prior prediction

Flickr is a photo/video hosting website having over 87 million users. Over 3.5 million new photos are uploaded daily. Currently there is no tool to organize these huge number of users in terms of their aesthetic tendency. Although Flickr allows users to manually join in different groups, they are laborious to maintain and should be updated when new users are added or removed. In this paper, we propose to classify Flickr users into a series of circles. Each circle contains users with similar aesthetic tendencies. We observed that: 1) an idea aesthetic model should be flexible, this is because different visual features are usually representative toward different data sets, and 2) the numbers of photos from different Flickr users vary remarkably. In this work, a novel probabilistic topic model is proposed to describe the aesthetic interest of each Flickr user as a distribution in the latent space. Afterward, an affinity graph is constructed to describe the similarity in terms of aesthetic interests among Flickr users. It is apparently that, densely linked Flickr users are with similar aesthetic interests. Therefore, these users are grouped into different Flickr circles based on an efficient dense graph discovery. The pipeline of the proposed Flickr circles discovery is fully automatic. Extensive experiments shown that our proposed method accurately mines Flickr circles from 60,000 Flickr users. Both BER and F 1 scores demonstrated that our Flickr circle discovery algorithm outperform 11 other popular community detection algorithms. Furthermore, the adopted regularized topic model is more effective than several well-known topic models such as pLSA and LDA.

/pdf/retracted-article-image-quality-tendency-modeling-by-fusing-48mah5ne9t.pdf

Jun Li

Papers

RETRACTED ARTICLE: Moving object surveillance using object proposals and background prior prediction

RETRACTED ARTICLE: Image quality tendency modeling by fusing multiple visual cues