Xingang Wang

Online State-Based Structured SVM Combined With Incremental PCA for Robust Visual Tracking

In this paper, we propose a robust state-based structured support vector machine (SVM) tracking algorithm combined with incremental principal component analysis (PCA). Different from the current structured SVM for tracking, our method directly learns and predicts the objects states and not the 2-D translation transformation during tracking. We define the objects virtual state to combine the state-based structured SVM and incremental PCA. The virtual state is considered as the most confident state of the object in every frame. The incremental PCA is used to update the virtual feature vector corresponding to the virtual state and the principal subspace of the objects feature vectors. In order to improve the accuracy of the prediction, all the feature vectors are projected onto the principal subspace in the learning and prediction process of the state-based structured SVM. Experimental results on several challenging video sequences validate the effectiveness and robustness of our approach.

Robust Visual Detection–Learning–Tracking Framework for Autonomous Aerial Refueling of UAVs

In this paper, we propose a robust visual detection-learning-tracking framework for autonomous aerial refueling of unmanned aerial vehicles. Two classifiers (D-classifier and T-classifier) are defined in the proposed framework. The D-classifier is a robust linear support vector machine (SVM) classifier trained offline for detecting the drogue object of aerial refueling and a low-dimensional normalized robust local binary pattern feature is proposed to describe the drogue object in the D-classifier. The T-classifier is a state-based structured SVM classifier trained online for tracking the drogue object. A combination strategy between the D-classifier and the T-classifier is proposed in the framework. The D-classifier is used to assess if some positive support vectors in the T-classifier are required to be replaced by positive examples with density peaks. The experimental results on several challenging video sequences validate the effectiveness and robustness of our proposed framework.

Detection and Tracking Strategies for Autonomous Aerial Refuelling Tasks Based on Monocular Vision

Detection and tracking strategies based on monocular vision are proposed for autonomous aerial refuelling tasks. The drogue attached to the fuel tanker aircraft has two important features. The grey values of the drogues inner part are different from the external umbrella ribs, as shown in the image. The shape of the drogues inner dark part is nearly circular. According to crucial prior knowledge, the rough and fine positioning algorithms are designed to detect the drogue. Particle filter based on the drogues shape is proposed to track the drogue. A strategy to switch between detection and tracking is proposed to improve the robustness of the algorithms. The inner dark part of the drogue is segmented precisely in the detecting and tracking process and the segmented circular part can be used to measure its spatial position. The experimental results show that the proposed method has good performance in real-time and satisfied robustness and positioning accuracy.

Aerial refueling drogue detection based on sliding-window object detector and hybrid features

In order to present an aerial refueling drogue detector, we use a sliding-window object detection framework, while using hybrid features of the sub-image in the detecting windows. Image processing technique and wavelet filter technique are used in the process of feature extraction, to form hybrid feature set. Feature selection depending on AdaBoost is used in the process of feature subset selection. The detection of the black center of drogue is in conjunction with the determination of the external umbrella area. Our aerial refueling drogue detection works well in a variety of illumination environment as well as works with high computational efficiency.

Face Detection With Different Scales Based on Faster R-CNN

In recent years, the application of deep learning based on deep convolutional neural networks has gained great success in face detection. However, one of the remaining open challenges is the detection of small-scaled faces. The depth of the convolutional network can cause the projected feature map for small faces to be quickly shrunk, and most detection approaches with scale invariant can hardly handle less than

Pose Measurement of Drogue via Monocular Vision for Autonomous Aerial Refueling

15\times 15

Real-time vehicle counting method based on image sequences with laser line

pixel faces. To solve this problem, we propose a different scales face detector (DSFD) based on Faster R-CNN. The new network can improve the precision of face detection while performing as real-time a Faster R-CNN. First, an efficient multitask region proposal network (RPN), combined with boosting face detection, is developed to obtain the human face ROI. Setting the ROI as a constraint, an anchor is inhomogeneously produced on the top feature map by the multitask RPN. A human face proposal is extracted through the anchor combined with facial landmarks. Then, a parallel-type Fast R-CNN network is proposed based on the proposal scale. According to the different percentages they cover on the images, the proposals are assigned to three corresponding Fast R-CNN networks. The three networks are separated through the proposal scales and differ from each other in the weight of feature map concatenation. A variety of strategies is introduced in our face detection network, including multitask learning, feature pyramid, and feature concatenation. Compared to state-of-the-art face detection methods such as UnitBox, HyperFace, FastCNN, the proposed DSFD method achieves promising performance on popular benchmarks including FDDB, AFW, PASCAL faces, and WIDER FACE.

Plane measurement based on monocular vision: Plane measurement based on monocular vision

In the probe-and-drogue refueling system, pilots need to operate carefully to dock probe with drogue, autonomous aerial refueling technology can assistant pilots to accomplish this operation. In this paper, we proposed a novel framework to measure pose of drogue via monocular vision, pose information of drogue can further lead control system accomplish aerial refueling automatically. This framework is consisted of three parts: detecting landmarks of drogue, locating contour of drogue in image, figuring out pose of drogue. Experiment results indicate that this pose measurement system is both accurate and efficient.

Automatic gear sorting system based on monocular vision

Being robust to changeable illumination and shadow are essential requirements of a practical vehicle counting system. In this paper, we come up with a method that detects vehicle by analyzing the state of laser line projected on lane. In addition, we use the entropy of histogram of oriented gradients (HOG) descriptor extracted from the region of interest (ROI) to quantify area percent of vehicle in a ROI. Normalized HOG descriptor is with better invariance to illumination and shadow, which makes a great contribution to the robustness of our method. Once the laser line disappears or appears in an image, we use entropy of HOG to judge that whether a vehicle is driving into or driving out of the ROI. We tested this method under different conditions, experimental results also prove that our method is robust to the change of illumination, and shadow of vehicles has no impact on accuracy and recall rate of detection result.