Shaoyi Li

Bio: Shaoyi Li is an academic researcher. The author has contributed to research in topics: Initialization & Superposition principle. The author has an hindex of 2, co-authored 3 publications receiving 5 citations.

Learning to Track Aircraft in Infrared Imagery

Abstract: Airborne target tracking in infrared imagery remains a challenging task. The airborne target usually has a low signal-to-noise ratio and shows different visual patterns. The features adopted in the visual tracking algorithm are usually deep features pre-trained on ImageNet, which are not tightly coupled with the current video domain and therefore might not be optimal for infrared target tracking. To this end, we propose a new approach to learn the domain-specific features, which can be adapted to the current video online without pre-training on a large datasets. Considering that only a few samples of the initial frame can be used for online training, general feature representations are encoded to the network for a better initialization. The feature learning module is flexible and can be integrated into tracking frameworks based on correlation filters to improve the baseline method. Experiments on airborne infrared imagery are conducted to demonstrate the effectiveness of our tracking algorithm.

Aerial infrared target tracking method based on KCF for frequency-domain scale estimation.

Abstract: The kernel correlation filter (KCF) tracking algorithm encounters the issue of tracking accuracy degradation due to large changes in scale and rotation of aerial infrared targets. Therefore, this paper proposes a new scale estimation KCF-based aerial infrared target tracking method, which can extract scale feature information of images in the frequency domain based on the distribution characteristics and change laws of frequency-domain energy. In addition, the proposed method can improve the accuracy of target scale information estimation. First, the KCF tracking algorithm is used to obtain the target position. Then, spectral eigenvalues are calculated as eigenvectors, and frequency-domain rotation scale invariance is adopted to extract the eigenvector between two frames as the target rotation change information. Reverse rotation is performed on the current frame spectrum map for isolating the effects of target rotation on scale information estimation. Then, the current target scale is estimated on the basis of the eigenvectors between the adjacent frames. Finally, the length-to-width ratio and the scale of the tracking box are updated on the basis of the target rotation information, which improves the adaptability of the tracking box to changes in the target scale and rotation. The results indicate that the proposed algorithm is suitable for stable tracking of target scales and rapid changes in attitudes. The average tracking accuracy and the average success rate of the algorithm are 0.954 and 0.782, which represent improvements of 5.3% and 18.9%, respectively, compared with the KCF algorithm. The average tracking success rate is improved by 4.1% compared with the discriminative scale space tracker algorithm, and the average tracking performance is better than that of related filter tracking algorithms based on other scale estimation methods.

Target detection and tracking based on spatially multiplexed and superposition imaging

Abstract: Addressing continuous target detection and tracking over a large field of view in surveillance application, a novel method to detect and track target is presented in a wide field of view based on spatially multiplexed and superposition imaging technique. This system architecture is proposed by using the spherical lens array and confocal plane with the character of wide field and compressive sampling. And the method of moving target detection with superposition imaging is studied emphatically. This method models each pixel as a Gaussian mixture model, while the Gaussian distributions are evaluated to determine which are most likely to result from a background process. Accordingly the background and foreground are separated. Also, the method of moving target decoding and tracking is researched, which means that target location is decoded based on a set resulting from classifying target copies according to position and velocity criteria in the superposition space. Finally, the target detection and decoding algorithm are simulated and the results show that this method can perform target detection and tracking over a wide field of view.

An adaptive optical flow technique for person tracking systems

Abstract: Optical flow can be used to segment a moving object from its background provided the velocity of the object is distinguishable from that of the background, and has expected characteristics. Existing optical flow techniques often detect flow (and thus the object) in the background. To overcome this, we propose a new optical flow technique, which only determines optical flow in regions of motion. We also propose a method by which output from a tracking system can be fed back into the motion segmenter/optical flow system to reinforce the detected motion, or aid in predicting the optical flow. This technique has been developed for use in person tracking systems, and our testing shows that for this application it is more effective than other commonly used optical flow techniques. When tested within a tracking system, it works with an average position error of less than six and a half pixels, outperforming the current CAVIAR1 benchmark system.

Optically multiplexed imaging with superposition space tracking

Abstract: We describe a novel method to track targets in a large field of view. This method simultaneously images multiple, encoded sub-fields of view onto a common focal plane. Sub-field encoding enables target tracking by creating a unique connection between target characteristics in superposition space and the target's true position in real space. This is accomplished without reconstructing a conventional image of the large field of view. Potential encoding schemes include spatial shift, rotation, and magnification. We briefly discuss each of these encoding schemes, but the main emphasis of the paper and all examples are based on one-dimensional spatial shift encoding. Simulation results are included to show the efficacy of the proposed sub-field encoding scheme.

The Use of UAV with Infrared Camera and RFID for Airframe Condition Monitoring

Abstract: The new progressive smart technologies announced in the fourth industrial revolution in aviation—Aviation 4.0—represent new possibilities and big challenges in aircraft maintenance processes. The main benefit of these technologies is the possibility to monitor, transfer, store, and analyze huge datasets. Based on analysis outputs, there is a possibility to improve current preventive maintenance processes and implement predictive maintenance processes. These solutions lower the downtime, save manpower, and extend the components’ lifetime; thus, the maximum effectivity and safety is achieved. The article deals with the possible implementation of an unmanned aerial vehicle (UAV) with an infrared camera and Radio Frequency Identification (RFID) as two of the smart hangar technologies for airframe condition monitoring. The presented implementations of smart technologies follow up the specific results of a case study focused on trainer aircraft failure monitoring and its impact on maintenance strategy changes. The case study failure indexes show the critical parts of aircraft that are subjected to damage the most. The aim of the article was to justify the need for thorough monitoring of critical parts of the aircraft and then analyze and propose a more effective and the most suitable form of technical condition monitoring of aircraft critical parts. The article describes the whole process of visual inspection performed by an unmanned aerial vehicle (UAV) with an IR camera and its related processes; in addition, it covers the possible usage of RFID tags as a labeling tool supporting the visual inspection. The implementations criteria apply to the repair and overhaul small aircraft maintenance organization, and later, it can also increase operational efficiency. The final suggestions describe the possible usage of proposed solutions, their main benefits, and also the limitations of their implementations in maintenance of trainer aircraft.

Real-Time Monocular Vision System for UAV Autonomous Landing in Outdoor Low-Illumination Environments

Abstract: Landing an unmanned aerial vehicle (UAV) autonomously and safely is a challenging task. Although the existing approaches have resolved the problem of precise landing by identifying a specific landing marker using the UAV’s onboard vision system, the vast majority of these works are conducted in either daytime or well-illuminated laboratory environments. In contrast, very few researchers have investigated the possibility of landing in low-illumination conditions by employing various active light sources to lighten the markers. In this paper, a novel vision system design is proposed to tackle UAV landing in outdoor extreme low-illumination environments without the need to apply an active light source to the marker. We use a model-based enhancement scheme to improve the quality and brightness of the onboard captured images, then present a hierarchical-based method consisting of a decision tree with an associated light-weight convolutional neural network (CNN) for coarse-to-fine landing marker localization, where the key information of the marker is extracted and reserved for post-processing, such as pose estimation and landing control. Extensive evaluations have been conducted to demonstrate the robustness, accuracy, and real-time performance of the proposed vision system. Field experiments across a variety of outdoor nighttime scenarios with an average luminance of 5 lx at the marker locations have proven the feasibility and practicability of the system.

Learning Spatio-Temporal Attention Based Siamese Network for Tracking UAVs in the Wild

Abstract: The popularity of unmanned aerial vehicles (UAVs) has made anti-UAV technology increasingly urgent. Object tracking, especially in thermal infrared videos, offers a promising solution to counter UAV intrusion. However, troublesome issues such as fast motion and tiny size make tracking infrared drone targets difficult and challenging. This work proposes a simple and effective spatio-temporal attention based Siamese method called SiamSTA, which performs reliable local searching and wide-range re-detection alternatively for robustly tracking drones in the wild. Concretely, SiamSTA builds a two-stage re-detection network to predict the target state using the template of first frame and the prediction results of previous frames. To tackle the challenge of small-scale UAV targets for long-range acquisition, SiamSTA imposes spatial and temporal constraints on generating candidate proposals within local neighborhoods to eliminate interference from background distractors. Complementarily, in case of target lost from local regions due to fast movement, a third stage re-detection module is introduced, which exploits valuable motion cues through a correlation filter based on change detection to re-capture targets from a global view. Finally, a state-aware switching mechanism is adopted to adaptively integrate local searching and global re-detection and take their complementary strengths for robust tracking. Extensive experiments on three anti-UAV datasets nicely demonstrate SiamSTA’s advantage over other competitors. Notably, SiamSTA is the foundation of the 1st-place winning entry in the 2nd Anti-UAV Challenge.