Yandong Tang

Flow mosaicking: Real-time pedestrian counting without scene-specific learning

In this paper, we present a novel algorithm based on flow velocity field estimation to count the number of pedestrians across a detection line or inside a specified region. We regard pedestrians across the line as fluid flow, and design a novel model to estimate the flow velocity field. By integrating over time, the dynamic mosaics are constructed to count the number of pixels and edges passed through the line. Consequentially, the number of pedestrians can be estimated by quadratic regression, with the number of weighted pixels and edges as input. The regressors are learned off line from several camera tilt angles, and have taken the calibration information into account. We use tilt-angle-specific learning to ensure direct deployment and avoid overfitting while the commonly used scene-specific learning scheme needs on-site annotation and always trends to overfitting. Experiments on a variety of videos verified that the proposed method can give accurate estimation under different camera setup in real-time.

Tricolor Attenuation Model for Shadow Detection

Shadows, the common phenomena in most outdoor scenes, bring many problems in image processing and computer vision. In this paper, we present a novel method focusing on extracting shadows from a single outdoor image. The proposed tricolor attenuation model (TAM) that describe the attenuation relationship between shadow and its nonshadow background is derived based on image formation theory. The parameters of the TAM are fixed by using the spectral power distribution (SPD) of daylight and skylight, which are estimated according to Plancks blackbody irradiance law. Based on the TAM, a multistep shadow detection algorithm is proposed to extract shadows. Compared with previous methods, the algorithm can be applied to process single images gotten in real complex scenes without prior knowledge. The experimental results validate the performance of the model.

Video Anomaly Search in Crowded Scenes via Spatio-Temporal Motion Context

Video anomaly detection plays a critical role for intelligent video surveillance. We present an abnormal video event detection system that considers both spatial and temporal contexts. To characterize the video, we first perform the spatio-temporal video segmentation and then propose a new region-based descriptor called “Motion Context,” to describe both motion and appearance information of the spatio-temporal segment. For anomaly measurements, we formulate the abnormal event detection as a matching problem, which is more robust than statistic model-based methods, especially when the training dataset is of limited size. For each testing spatio-temporal segment, we search for its best match in the training dataset, and determine how normal it is using a dynamic threshold. To speed up the search process, compact random projections are also adopted. Experiments on the benchmark dataset and comparisons with the state-of-the-art methods validate the advantages of our algorithm.

A Stairway Detection Algorithm based on Vision for UGV Stair Climbing

In the paper, we present a vision based algorithm used to guide the unmanned ground vehicles (UGV) for autonomous stairways climbing and implement it on UGV successfully. The reliability of guiding UGV to climb stairs requires evaluating two offset parameters: the position of vehicle on stairs and the orientation angle to stairs. The intention of our algorithm is to estimate these two parameters through extracting the stair edges robustly. To achieve this goal, we apply the Gabor filter to eliminate the influence of the illumination and keep edges, and propose a fast method to remove small lines. Finally we link stair edges, and estimate the offset parameters used to steer the vehicle by RANSAC algorithm. Experiments on various stairways including indoor and outdoor are given in various light conditions. The results validate our algorithm.

RGBD Salient Object Detection via Deep Fusion

Numerous efforts have been made to design various low-level saliency cues for RGBD saliency detection, such as color and depth contrast features as well as background and color compactness priors. However, how these low-level saliency cues interact with each other and how they can be effectively incorporated to generate a master saliency map remain challenging problems. In this paper, we design a new convolutional neural network (CNN) to automatically learn the interaction mechanism for RGBD salient object detection. In contrast to existing works, in which raw image pixels are fed directly to the CNN, the proposed method takes advantage of the knowledge obtained in traditional saliency detection by adopting various flexible and interpretable saliency feature vectors as inputs. This guides the CNN to learn a combination of existing features to predict saliency more effectively, which presents a less complex problem than operating on the pixels directly. We then integrate a superpixel-based Laplacian propagation framework with the trained CNN to extract a spatially consistent saliency map by exploiting the intrinsic structure of the input image. Extensive quantitative and qualitative experimental evaluations on three data sets demonstrate that the proposed method consistently outperforms the state-of-the-art methods.

V-disparity Based UGV Obstacle Detection in Rough Outdoor Terrain

This paper presents a fast obstacle detection system based on stereo vision for unmanned ground vehicle (UGV) navigation in unstructured environment.In order to make the UGV adaptable to more complex terrains,we propose a new estimation method of the main ground disparity (MGD) from the V-disparity images.Then,by comparing the disparity of the MGD with local 3D reconstruction,a coarse-to-fine method to find and localize obstacles is introduced in the paper.The obstacle detection system is tested practically on our UGV platform in some outdoor unstructured environments.The experimental results validate the effcacy of our system.

Skew detection in document images based on rectangular active contour

The digitalization processes of documents produce frequently images with small rotation angles. The skew angles in document images degrade the performance of optical character recognition (OCR) tools. Therefore, skew detection of document images plays an important role in automatic document analysis systems. In this paper, we propose a Rectangular Active Contour Model (RAC Model) for content region detection and skew angle calculation by imposing a rectangular shape constraint on the zero-level set in Chan–Vese Model (C-V Model) according to the rectangular feature of content regions in document images. Our algorithm differs from other skew detection methods in that it does not rely on local image features. Instead, it uses global image features and shape constraint to obtain a strong robustness in detecting skew angles of document images. We experimented on different types of document images. Comparing the results with other skew detection algorithms, our algorithm is more accurate in detecting the skews of the complex document images with different fonts, tables, illustrations, and layouts. We do not need to pre-process the original image, even if it is noisy, and at the same time the rectangular content region of a document image is also detected.

Outdoor shadow detection by combining tricolor attenuation and intensity

Shadow detection is of broad interest in computer vision. In this article, a new shadow detection method for single color images in outdoor scenes is proposed. Shadows attenuate pixel intensity, and the degrees of attenuation are different in the three RGB color channels. Previously, we proposed the Tricolor Attenuation Model (TAM) that describes the attenuation relationship between shadows and their non-shadow backgrounds in the three color channels. TAM can provide strong information on shadow detection; however, our previous study needs a rough segmentation as the pre-processing step and requires four thresholds. These shortcomings can be overcome by adding intensity information. This article addresses the problem of how to combine TAM and intensity and meanwhile to obtain a threshold for shadow segmentation. Simple and complicated shadow images are used to test the proposed method. The experimental results and comparisons validate its effectiveness.

New spectrum ratio properties and features for shadow detection

Successfully detecting shadows in still images is challenging yet has wide applications. Shadow properties and features are very important for shadow detection and processing. The aim of this work is to find some new physical properties of shadows and use them as shadow features to design an effective shadow detection method for outdoor color images. We observe that although the spectral power distribution (SPD) of daylight and that of skylight are quite different, in each channel, the spectrum ratio of the point-wise product of daylight SPD with sRGB color matching functions (CMFs) to the point-wise product of skylight SPD with sRGB CMFs roughly approximates a constant. This further leads to that the ratios of linear sRGB pixel values of surfaces illuminated by daylight (in non-shadow regions) to those illuminated by skylight (in shadow regions) equal to a constant in each channel. Following this observation, we calculated the spectrum ratios under various Sun angles and further found out four new shadow properties. With these properties as shadow features, we developed a simple shadow detection method to quickly locate shadows in single still images. In our method, we classify an edge as a shadow or non-shadow edge by verifying whether the pixel values on both sides of the Canny edges satisfy the three shadow verification criteria derived from the shadow properties. Extensive experiments and comparison show that our method outperforms state-of-the-art shadow detection methods. HighlightsWe found the ratios of regions lit by daylight vs. by skylight equal to a constant.We calculated spectrum ratios and found out four new shadow properties.Following the new shadow properties, we proposed a simple shadow detection method.We conducted most extensive experiments and comparison.We also tested our method on images without shadows.

A robust template tracking algorithm with weighted active drift correction

In this paper, we propose a novel algorithm for object template tracking and its drift correction. It can prevent the tracking drift effectively, and save the time of an additional correction tracking. In our algorithm, the total energy function consists of two terms: the tracking term and the drift correction term. We minimize the total energy function synchronously for template tracking and weighted active drift correction. The minimization of the active drift correction term is achieved by the inverse compositional algorithm with a weighted L2 norm, which is incorporated into traditional affine image alignment (AIA) algorithm. Its weights can be adaptively updated for each template. For diminishing the accumulative error in tracking, we design a new template update strategy that chooses a new template with the lowest matching error. Finally, we will present various experimental results that validate our algorithm. These results also show that our algorithm achieves better performance than the inverse compositional algorithm for drift correction.