Although the performance of unmanned aerial vehicle (UAV) tracking has benefited from the successful application of discriminative correlation filters (DCF) and convolutional neural networks (CNNs), UAV tracking under occlusion and deformation remains a challenge. The main dilemma is that challenging scenes, such as occlusion or deformation, are very complex and changeable, making it difficult to obtain training data covering all situations, resulting in trained networks that may be confused by new contexts that differ from historical information. Data-driven strategies are the main direction of current solutions, but gathering large-scale datasets with object instances under various occlusion and deformation conditions is difficult and lacks diversity. This paper proposes an attention-based mask generation network (AMGN) for UAV-specific tracking, which combines the attention mechanism and adversarial learning to improve the tracker’s ability to handle occlusion and deformation. After the base CNN extracts the deep features of the candidate region, a series of masks are determined by the spatial attention module and sent to the generator, and the generator discards some features according to these masks to simulate the occlusion and deformation of the object, producing more hard positive samples. The discriminator seeks to distinguish these hard positive samples while guiding mask generation. Such adversarial learning can effectively complement occluded and deformable positive samples in the feature space, allowing to capture more robust features to distinguish objects from backgrounds. Comparative experiments show that our AMGN-based tracker achieves the highest area under curve (AUC) of 0.490 and 0.349, and the highest precision scores of 0.742 and 0.662, on the UAV123 tracking benchmark with partial and full occlusion attributes, respectively. It also achieves the highest AUC of 0.555 and the highest precision score of 0.797 on the DTB70 tracking benchmark with the deformation attribute. On the UAVDT tracking benchmark with the large occlusion attribute, it achieves the highest AUC of 0.407 and the highest precision score of 0.582.
Intra-body communication (IBC) is a technology using the conductive properties of the body to transmit signal, and information interaction by handshake is regarded as one of the important applications of IBC. In this paper, a method for modeling the galvanic coupling intra-body communication via handshake channel is proposed, while the corresponding parameters are discussed. Meanwhile, the mathematical model of this kind of IBC is developed. Finally, the validity of the developed model has been verified by measurements. Moreover, its characteristics are discussed and compared with that of the IBC via single body channel. Our results indicate that the proposed method will lay a foundation for the theoretical analysis and application of the IBC via handshake channel.
Although Siamese trackers have recently been gradually replaced by complicated and computationally expensive Transformer trackers, they are simpler and more applicable to real-world deployment. We believe that room for improvement still exists in the Siamese tracking framework and attribute the performance limitation to inadequate annotation, insufficient augmentation and suboptimal assignment, which heavily weakens the discriminative power. As Siamese methods directly inherit the assignment manner from object detection, they both face the imbalance between sparse annotated objects and dense background examples and between easy and hard negative examples. Moreover, existing augmentations and negative pairs are insufficient to simulate practical tracking ambiguity and failure cases. Nevertheless, work in the training vein is still overlooked. Therefore, we strive to yield a negative-driven training pipeline to unleash the potential of the Siamese framework without any extra inference cost. Specifically, 1) We devise strong negative augmentations based on random copy-paste to take full advantage of available annotations and generate more challenging tracking scenarios, especially negative examples. 2) We propose a semisupervised two-phase assignment that jointly utilizes existing annotations and model outputs to mine more appropriate and challenging negative examples. 3) We formulate a complementary reweighting loss by modifying the loss weight matrix to bridge subtasks and highlight the contributions of hard negative examples more smoothly. We choose several classic Siamese trackers to validate the pipeline effectiveness. After training, these trackers can gain, at most, a nearly 14% relative increase in performance, which is comparable to advanced Siamese trackers and even Transformer trackers. The experimental results indicate that the tracking-specific training pipeline is an efficient method for strengthening trackers and requires further development.
Quantification of image clutter plays an important role in predicting target acquisition performances of a photoelectric imaging system due to the strong effect of optoelectronic image clutter. Accuracy in predicting the targeting performance of previous reported clutter metrics was relatively low because of disadvantages, such as lack of ability to accurately quantify the image with complex clutters and threshold selection problem. To address this problem, a novel multidirectional-difference-Hash-based image clutter metric is proposed in this paper. Initially, an image similarity measure method based on multidirectional difference hash is established. Then, this method is applied to the quantification of image clutter, and an MDHash-based image clutter metric is obtained. A comparative experiment is conducted using Search_2 dataset. Results show that the proposed clutter metric correlates effectively with probability of detection, false alarm rate, and search time of observers.
In this paper, an infrared target adaptive detection method based on the receptive field and lateral inhibition (LI) of the human visual system is proposed. In the proposed method, the direction parameters of a Gabor filter are adaptively determined according to the gradient direction, so that edges in the image can be detected without manual intervention. Meanwhile, background prediction based on LI is used for regulating the gray value in the image to achieve background suppression and target enhancement. Experimental results indicate that the proposed method can extract both the small target and the area target from a complex background, and has satisfactory target detection ability.