Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using metrics using the precision, accuracy, sensitivity, specificity, and DICE coefficient (DC). The DC ranged from 0.7354±0.1149 to 0.8372±0.0858. The DC of the best method was close to the inter-observer agreement (0.8398±0.0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better (p<0.01) than single model methods, with mean DC of 0.7966 and 0.7544, respectively. Deep learning based methods could potentially help pathologists find suspicious regions for further analysis of lung cancer in WSI.

Convolutional neural networks (CNNs) have been adopted in monocular satellite pose estimation and achieve superior performance over traditional methods. However, existing CNN-based methods suffer from bias toward texture, indirect description of absolute distance, and lack of long-range dependence modeling. Such factors limit the generalizability of CNN-based methods. Motivated by the striking achievements of transformer models, this article adopts transformer blocks for satellite pose estimation from a single RGB image, proposing an efficient monocular satellite pose estimation method. First, we design an effective satellite representation model based on a set of keypoints. Then, considering monocular satellite pose estimation characteristics, we construct an end-to-end keypoint-set prediction network and build the bipartite loss function. Further, we improve the backbone structure for high-quality feature extraction. Experimental results on a public benchmark dataset indicate that the proposed method achieves second and third place on the synthetic and real test sets, respectively, using only synthetic training data. We also demonstrate that our keypoint predictor takes half as much time as the first-placed method in our comparison, and therefore achieves a better tradeoff between speed and accuracy than existing approaches.

Factors, such as rapid relative motion, clutter background, etc., make robust small aerial target detection for airborne infrared detection systems a challenge. Existing methods are facing difficulties when dealing with such cases. We consider that a continuous and smooth trajectory is critical in boosting small infrared aerial target detection performance. A simple and effective small aerial target detection method for airborne infrared detection system using light gradient boosting model (LightGBM) and trajectory constraints is proposed in this article. First, we simply formulate target candidate detection as a binary classification problem. Target candidates in every individual frame are detected via interesting pixel detection and a trained LightGBM model. Then, the local smoothness and global continuous characteristic of the target trajectory are modeled as short-strict and long-loose constraints. The trajectory constraints are used efficiently for detecting the true small infrared aerial targets from numerous target candidates. Experiments on public datasets demonstrate that the proposed method performs better than other existing methods. Furthermore, a public dataset for small aerial target detectionin airborne infrared detection systems is constructed. To the best of our knowledge, this dataset has the largest data scale and richest scene types within this field.

Due to the lack of distinctiveness to the background, robust monocular 6DOF pose tracking of less-distinct objects remains an important open problem. In this paper, we firstly analyze the object distinctiveness in the tracking process. Then, we propose a novel contour-part model based robust monocular pose tracking method for less-distinct objects. This paper uses the traditional contour feature for pose tracking in a novel strategy called contour part model. First, the contour part model is built by segmenting the projected contour rendered from the 3D model into contour segments of a certain length adaptively according to the Shi-Tomasi cornerness scores. Then, the correspondence is detected in the input image for each contour part by gradient orientation based template matching. Finally, pose tracking is achieved by solving the PnP problem. Experiment results on semi-synthetic and real images show that the proposed method performs better than the existing methods when pose tracking less-distinct objects and shows great robustness toward interference. Additionally, we combine the edge feature and the regional feature in a simple strategy. The overall performance of the fused method is boosted according to the experimental results on the RBOT dataset. The fact shows that the fusion of the edge and regional features has great potential for improving tracking performance.

Tracking the pose of a specific rigid object from monocular sequences is a basic problem in computer vision. State-of-the-art methods assume motion continuity between two consecutive frames. However, drastic relative motion causes large interframe pose shifts, especially in applications such as robotic grasping, failed satellite maintenance, and space debris removal. Large pose shifts interrupt the interframe motion continuity leading to tracking failure. In this article, we propose a robust and accurate monocular pose tracking method for tracking objects with large pose shifts. Using an indexable sparse viewpoint model to represent the object 3D geometry, we propose establishing a transitional view, which is searched for in an efficient variable-step way, to recover motion continuity. Then, a region-based optimization algorithm is adopted to optimize the pose based on the transitional view. Finally, we use a single-rendering-based pose refinement process to achieve highly accurate pose results. The experiments on the region-based object tracking (RBOT) dataset, the modified RBOT dataset, the synthetic large pose shift sequences, and real sequences demonstrated that the proposed method achieved superior performance to the state-of-the-art methods in tracking objects with large pose shifts.

The random sample consensus (RANSAC) based algorithm is widely used in estimating the two-view geometry from image point correspondences. However, it often becomes extremely slow when the data is contaminated by a large percentage of incorrect matches. To address this problem, the paper proposes a new modification of RANSAC called LP-RANSAC that is robust to varying inlier ratios and achieves large computational savings without deterioration in accuracy. LP-RANSAC integrates the locality preserving constraint into the universal RANSAC framework, which prunes most of the unreliable correspondences before the hypothesize-and-verify loop and guides non-uniform sampling to generate and verify promising models earlier. Unlike other guided sampling strategies, the proposed method is simple to implement and does not require any prior information. Extensive experiments performed on the publicly available datasets reveal that LP-RANSAC can achieve more accurate and stable solutions at much lower computational cost (in milliseconds on standard CPU) than state-of-the-art methods, particularly when handling problems with low inlier ratios.