Although visual surveillance has emerged as an effective technolody for public security, privacy has become an issue of great concern in the transmission and distribution of surveillance videos. For example, personal facial images should not be browsed without permission. To cope with this issue, face image scrambling has emerged as a simple solution for privacy-related applications. Consequently, online facial biometric verification needs to be carried out in the scrambled domain, thus bringing a new challenge to face classification. In this paper, we investigate face verification issues in the scrambled domain and propose a novel scheme to handle this challenge. In our proposed method, to make feature extraction from scrambled face images robust, a biased random subspace sampling scheme is applied to construct fuzzy decision trees from randomly selected features, and fuzzy forest decision using fuzzy memberships is then obtained from combining all fuzzy tree decisions. In our experiment, we first estimated the optimal parameters for the construction of the random forest and, then, applied the optimized model to the benchmark tests using three publically available face datasets. The experimental results validated that our proposed scheme can robustly cope with the challenging tests in the scrambled domain and achieved an improved accuracy over all tests, making our method a promising candidate for the emerging privacy-related facial biometric applications.

/pdf/privacy-protected-facial-biometric-verification-using-fuzzy-588zeucii9.pdf

Privacy-Protected Facial Biometric Verification Using Fuzzy Forest Learning

Pool and billiards are amongst a family of games played on a table with six pockets along the rails. This paper presents an augmented reality tool designed to assist unskilled or amateur players of such games. The system is based on a projector and a Kinect 2 sensor placed above the table, acquiring and processing the game on-the-fly. By using depth information and detecting the table’s rails (borders), the balls’ positions, the cue direction, and the strike of the ball, computations predict the resulting balls’ trajectories after the shot is played. These results—trajectories, visual effects, and menus—are visually output by the projector, making them visible on the snooker table. The system achieves a shot prediction accuracy of 98% when no bouncing occurs.

/pdf/augmented-reality-system-to-assist-inexperienced-pool-2nfzpm7s72.pdf

Augmented reality system to assist inexperienced pool players

Low-quality facial biometric verification via dictionary-based random pooling

Undersea/subsea data collection via automated underwater vehicles (AUVs) plays an important role for marine biodiversity research, while it is often much more challenging than the data collection above ground via satellites or AUVs. To enable the automated undersea/subsea data collection system, the AUVs are expected to be able to automatically track the objects of interest through what they can “see” from their mounted underwater cameras, where videos or images could be drastically blurred and degraded in underwater lighting conditions. To solve this challenge, in this work, we propose a cascaded framework by combining a DCGAN (deep convolutional generative adversarial network) with an object detector, i.e., single-shot detector (SSD), named DCGAN+SSD, for the detection of various underwater targets from the mounted camera of an automated underwater vehicle. In our framework, our assumption is that DCGAN can be leveraged to alleviate the impact of underwater conditions and provide the object detector with a better performance for automated AUVs. To optimize the hyperparameters of our models, we applied a particle swarm optimization (PSO)-based strategy to improve the performance of our proposed model. In our experiments, we successfully verified our assumption that the DCGAN+SSD architecture can help improve the object detection toward the undersea conditions and achieve apparently better detection rates over the original SSD detector. Further experiments showed that the PSO-based optimization of our models could further improve the model in object detection toward a more robust and fair performance, making our work a promising solution for tackling the challenges in AUVs.

/pdf/robust-and-fair-undersea-target-detection-with-automated-39owbt84.pdf

Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection

Real-time traffic analysis using the road mounted surveillance cameras present multitude of benefits. This kind of traffic video processing has become an important means for intelligent traffic management and control. The estimation and analysis of road traffic motion is an involved task in computer vision and video processing. In our work, morphological operations and region growing method are used to perform salient motion detection of objects. In classical background extraction method, the background has to be learnt from large numbers of frames. In our method, no a prior knowledge about shape and size of object is acquired. Instead, sum of square difference is estimated via online learning for the calculation of the centroid distance. The test results indicate that the road vehicles and their statistics are determined through our algorithm with complete fidelity.

Traffic Flow Estimation from Road Surveillance

Automated 3-D modeling from real sports videos can provide useful resources for visual design in sports-related computer games, saving a lot of effort in manual design of visual contents. However, image-based 3-D reconstruction usually suffers from inaccuracy caused by statistic image analysis. In this paper, we propose an information-theoretical scheme to minimize errors of automated 3-D modeling from monocular sports videos. In the proposed scheme, mutual information (MI) was exploited to compute the fitting scores of a 3-D model against the observed single-view scene, and the optimization of model fitting was carried out subsequently. With this optimization scheme, errors in model fitting were minimized without human intervention, allowing automated reconstruction of 3-D animation from consecutive monocular video frames at high accuracy. In our work, the Snooker videos were taken as our case study, balls were positioned in 3-D space from single-view frames, and 3-D animation was reproduced from real Snooker videos. Our experimental results validated that the proposed information-theoretical scheme can help attain better accuracy in the automated reconstruction of 3-D animation, and demonstrated that information-theoretical evaluation can be an effective approach for model-based reconstruction from single-view videos.

Phillip A. Legg

Papers

Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization