Recent studies have shown impressive performance in object detection. However, most current detectors only explore the appearance feature to locate and classify objects but disregard or underestimate the valuable contextual information in the image, which limits the detection performance for those hard objects, such as small objects, occluded objects, blurred objects, etc. In this article, we instead seek to build a novel context modeling framework and conduct more effective context reasoning for object detection. Specifically, we design a Context-guided Reasoning Network (CRNet) to explore the relationships between objects and use easy detected objects to help understand hard ones. In our CRNet, an image is modeled as a graph and local features of objects are viewed as nodes of the graph to learn the relationships between objects. By passing contextual information in the built graph, the features of hard objects can be updated to discriminative features. To this end, we first develop a cascaded center prediction module built upon CenterNet to produce a set of high-quality proposals viewed as nodes of the graph. In addition, to maximize the value of global context information, we present a multi-granularity feature fusion network to encode the whole scene information which is also viewed as nodes of the graph. Then, the spatial and semantic relationships between objects are learned to initialize edges of the graph. Finally, context reasoning is conducted to update the node states iteratively. Extensive experiments are conducted on MS COCO and Pascal VOC to demonstrate the effectiveness of the proposed CRNet. Experimental results show that the proposed CRNet greatly improves the detection performance over existing context-based detectors, and it is comparable with state-of-the-art detectors.

Pedestrians are often vulnerable users of urban roads and ensuring their safety is a pressing challenge in the filed of intelligent transportation. Multiple pedestrian tracking is one of the key technologies for traffic statistics and abnormal behavior analysis, etc. Detection-based tracking methods have achieved remarkable results and have become mainstream processing schemes. However, target association is still immature and less effective in complex scenarios. In the proposed tracking system, several candidates surrounding each detected pedestrian are selected sparsely, and the associating relationship between the target and these candidates is determined based on a graph attention map. These graph attention maps contain positional correlations of the matching pairs and are applicable with pedestrians’ posture variations. The weighted correlating value is estimated with the positional weighted matrix and merged attention map. The correlating relationship is confirmed with the weighted correlating value and distance matching loss. To enhance the computation efficiency of the graph attention maps for these tracked targets and candidates, feature extraction is processed separately. Convolutional features extracted from one specific middle layer of the backbone network are used to represent each target or candidate. The experiment results show that the proposed tracker achieves better performance than the other five state-of-the-art trackers on three publicly available databases.

With the use of deep learning, object detection has achieved great breakthroughs. However, existing object detection methods still can not cope with challenging environments, such as dense objects, small objects, and object scale variations. To address these issues, this paper proposes a novel keypoint-based detection framework, called CrossNet, which significantly improves detection performance with minimal costs. In our approach, an object is modeled as a cross that consists of a center keypoint and a specific size, which eliminates the need of hand-craft anchor design. The proposed CrossNet outputs three types of maps: the center map, size map, and offset map, where both center map and offset map are to predict the center keypoints of objects and the size map is to estimate the sizes (width and height) of objects. Specifically, we first design a cascaded center prediction method that introduces a coarse-to-fine idea to improve center prediction. Furthermore, since center prediction considered as a classification task is easier than size regression relatively, we design a center-attention size regression module that uses the detection results of centers to assist the size prediction. In addition, a slightly modified hourglass network is designed to enhance the quality of feature maps for center and size prediction. Extensive experiments are conducted to demonstrate the effectiveness of CrossNet on the challenging PASCAL VOC, COCO, KITTI, and WiderFace datasets. Empirical studies show that CrossNet achieves competitive results with top-ranked one-stage and two-stage detectors while being time-efficient.

Finger vein has been proved to be an effective biometric for personal identification in recent years. Inspired by the good power of Gabor filter in capturing specific texture characteristics from any orientation of an image, this paper proposes a simple, yet powerful and efficient local descriptor for finger vein recognition, called histogram of competitive Gabor responses (HCGR). Specially, HCGR is based on a set of competitive Gabor response (CGR) which consists of two components: competitive Gabor magnitude (CGM) and competitive Gabor orientation (CGO). A set of CGR includes the information on magnitude and orientation of the maximum responses of the Gabor filter bank with a number of different orientations. For a given image, we calculate its CGM image and CGO image and represent them in a concatenated histogram, called HCGR. This histogram can efficiently and effectively exploit the discriminative orientation and local features in a finger vein image. The experimental results obtained on our publically available finger vein image database MMCBNU_6000 demonstrate that the proposed HCGR outperforms the classical local operators such as Gabor, steerable, histogram of oriented gradients (HOG) and local binary pattern (LBP).