Marine oil spills have become a significant threat to ocean environments and ecosystems. The development of effective marine oil spill identification technology is crucial for emergency authorities to enhance response strategies. In this letter, a marine oil spill detection method based on the histogram of oriented gradient (HOG) features, random forest classifier, and particle swarm optimization (PSO) algorithm was proposed. First, row vector convolution and mean filtering were adopted to extract and smooth the co-frequency interferences. Then, binarization processing and median filtering were used to eliminate speckles. After that, gray correction and contrast enhancement model were performed to enhance the overall oil slick features. Next, HOG features and random forest classifier were utilized to extract effective oil spill regions. Finally, the PSO algorithm was introduced to iteratively optimize the adaptive dual-threshold for segmenting the real oil slicks. This approach enables accurate and efficient detection of oil spills, offering a scientific foundation for responding to offshore oil spill incidents.

Automatic pain assessment is an application in healthcare serving personalized pain care, and patients cannot self-report pain. Pain at the present is inferred from physiological dynamics at the present and in the near past. However, heterogeneous pain responses cross-subject and cross-type hinder accurate recognition of pain. This work solves the adaptive pain recognition problem across pain types. We concrete the adaptivity problem into recognizing both phasic/short and tonic/long pain from the physiological sequences of the same length. The adaptivity of the proposed solution (TCAtt-PainNet) was ensured by hybrid temporal-channel attention when fusing multivariate time-series of electrocardiogram (ECG) and galvanic skin response (GSR) features. The attention was obtained by learning the dependencies between the point at present and the sequence in the near past, where sequence point temporal attention was constructed via modified self-attention, and the following feature channel attention was constructed by squeeze-and-excitation temporal attention weighted deep feature sequence. The proposed solution successfully enhanced recognition adaptivity by addressing relevant information only from long input sequences when testing with tonic and phasic pain databases, making progress towards automatic pain assessment for real application scenarios with attributes unknown pain.

This paper proposes a whole-body learning from demonstration (LfD) framework that enables differential drive mobile manipulators to learn coordination working and disturbance rejection. First, an efficient kinesthetic teaching method is devised based on the weighted least-norm (WLN) inverse kinematics solution and an admittance controller, which facilitates human users to guide the mobile manipulator to perform tasks. Second, we propose a whole-body LfD framework through Gaussian Process, which endows the mobile manipulator's skill learning process with features of large-scale convergence, coordination working and disturbance rejection, after just a few human demonstrations. The proposed learning framework also allows for human-in-the-loop correction when the whole-body is conducting a task. Finally, the effectiveness of the proposed framework is verified via two simulations and a pick-and-place experiment. Supplementary video for this paper is available in github††https://github.com/yuqiang-yang/SMC2023-Video.

Effective oil spill monitoring is critical for timely response to minimize the impact on the environment. In response to the difficulty in extracting suspected oil films from marine radar images, a semantic segmentation method was proposed. In the preprocessing of training samples in similar scene, a slicing solution was used to compensate for the small sample of original data. The U-Net semantic segmentation network was used to classify oil film into two categories: real and suspected. Existing mainstream marine radar oil spill identification methods were compared. Experimental results demonstrate that the proposed method achieves more reliability in oil spill semantic segmentation. It can provide real-time information for oil spill emergency response and disaster assessment.

Existing single image super-resolution methods are either designed for synthetic data, or for real data but in the RGB-to-RGB or the RAW-to-RGB domain. This paper proposes to zoom an image from RAW to RAW inside the camera imaging pipeline. The RAW-to-RAW domain closes the gap between the ideal and the real degradation models. It also excludes the image signal processing pipeline, which refocuses the model learning onto the super-resolution. To these ends, we design a method that receives a low-resolution RAW as the input and estimates the desired higher-resolution RAW jointly with the degradation model. In our method, two convolutional neural networks are learned to constrain the high-resolution image and the degradation model in lower-dimensional subspaces. This subspace constraint converts the ill-posed SISR problem to a well-posed one. To demonstrate the superiority of the proposed method and the RAW-to-RAW domain, we conduct evaluations on the RealSR and the SR-RAW datasets. The results show that our method performs superiorly over the state-of-the-arts both qualitatively and quantitatively, and it also generalizes well and enables zero-shot transfer across different sensors.