Propagation and association tasks in Multi-Object Tracking (MOT) play a pivotal role in accurately linking the trajectories of moving objects. Recently, modern deep learning models have been addressing these tasks by introducing fragmented solutions for each different problem such as appearance modeling, motion modeling, and object associations. To bring unification in the MOT task, we introduce a pixel-guided approach to efficiently build the joint-detection and tracking framework for multi-object tracking. Specifically, the up-sampled multi-scale features from consecutive frames are queued to detect the object locations by using a transformer–decoder, and per-pixel distributions are utilized to compute the association matrix according to object queries. Additionally, we introduce a long-term appearance association on track features to learn the long-term association of tracks against detections to compute the similarity matrix. Finally, a similarity matrix is jointly integrated with the Byte-Tracker resulting in a state-of-the-art MOT performance. The experiments with the standard MOT15 and MOT17 benchmarks show that our approach achieves significant tracking performance.

Motion blur, which disturbs human and machine perceptions of a scene, has been considered an unnecessary artifact that should be removed. However, the blur can be a useful clue to understanding the dynamic scene, since various sources of motion generate different types of artifacts. Motivated by the relationship between motion and blur, we propose a motion-aware feature learning framework for dynamic scene deblurring through multi-task learning. Our multi-task framework simultaneously estimates a deblurred image and a motion field from a blurred image. We design the encoder-decoder architectures for two tasks, and the encoder part is shared between them. Our motion estimation network could effectively distinguish between different types of blur, which facilitates image deblurring. Understanding implicit motion information through image deblurring could improve the performance of motion estimation. In addition to sharing the network between two tasks, we propose a reblurring loss function to optimize the overall parameters in our multi-task architecture. We provide an intensive analysis of complementary tasks to show the effectiveness of our multi-task framework. Furthermore, the experimental results demonstrate that the proposed method outperforms the state-of-the-art deblurring methods with respect to both qualitative and quantitative evaluations.

In this paper, we propose a highly feasible fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from single object trackers such as kernalized correlation filter, SiamRPN, and DaSiamRPN. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU-only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets.

Deep learning has recently made an impressive advance in ship detection in Synthetic Aperture Radar (SAR) images. Despite this advancement, conventional deep detection networks often suffer from speckle noise that inherently occurs in SAR images. However, despeckling researches have focused only on improving the visual quality of the SAR images. Despeckling without considering subsequent task may cause loss of semantic information and result in performance degradation. In this letter, we propose a deep cascade framework for noise-robust SAR ship detection that sequentially performs despeckle and detection. We effectively train our cascade network using pseudo-SAR images with SAR-like structures and additional detection annotations. We also propose semantic conservative loss that allows these two tasks to cooperate with each other. Experimental results including comparisons to previous methods and extensive ablation studies show the effectiveness of our proposed method.