Infrared small target detection (IRSTD) has been a long challenging task in infrared detection technology due to the inherently low contrast and absence of discernible texture in such targets. To address this issue, a new U-shaped segmentation network (CN-UNet) is proposed in this article. CN-UNet first employs the ConvNeXt module as the encoder, which implements a self-attention mechanism through pure convolutional operations, mirroring the Swin Transformer’s functionality while expanding the receptive field interactions of target features. This design not only optimizes computational efficiency but also enables multiscale feature identification across diverse dimensional contexts. Besides, a multiscale local contrast learning module (MSLCLM) is integrated into the encoder-decoder cross layer connections to selectively filter features aligned with human visual priors, thereby directing the network’s attention toward precise target localization. Finally, during the model inference, a slicing-aided hypersegmentation module is introduced to dynamically rescale output images through adaptive slicing operations, which could furtherly improve infrared target detection and segmentation performance. Comprehensive evaluations across three typical benchmarks demonstrate that the proposed CN-UNet is superior to other state-of-the-art IRSTD methods, with better visual quality and index evaluation metrics.

Vision-based myoelectric prosthetic hand uses a camera integrated into its body for object detection and environment understanding, where the results provide necessary information for grasp planning. It is expected that the semi-automatic prosthesis control can be realized with this method. However, such a control method usually suffers from heavy computation due to the requirement of real-time image processing to keep up with the arm movements of the user. This paper presents a distributed control system that assigns heavy processing tasks to one or multiple processing nodes through the network, which greatly reduces the computation burdens of the processor embedded in the prosthetic hand. In this control scheme, the embedded system in the prosthetic hand is only used for gathering necessary data for grasp planning, while the processing nodes in the network are responsible for processing and managing the collected data. A test platform is built to verify the proposed control scheme. The test platform streams user electromyography (EMG) signals and images simultaneously to the GPU server. The GPU sever analyzes the received data and generates the corresponding motor commands in real time. A case study that uses a 3-DoF gripper to continuously grasp several objects is performed using this test platform.

Conventional control systems for prosthetic hands use myoelectric signals as an interface, but it is impossible to realize complex and flexible human hand movements with only myoelectric signals. A promising control scheme for prosthetic hands uses computer vision to assist in grasping objects. It features an imaging sensor, and the control system is capable of recognizing an object placed in the environment. Then, a gripping pattern can be selected from some predefined candidates according the recognized object. However, previous studies assumed that only one object exists in the environment. If there are multiple target objects in the environment, the hand could become confused in attempting to find the target object. This study addresses this problem and proposes a method to determine the target object from multiple objects. The proposed method is able to determine the target object by estimating the positional relationship between the artificial hand and the objects, as well as the motion of the hand. To verify the validity and effectiveness, we implemented the proposed method in a vision-based prosthetic hands control system and conducted pick-and-place experiments. The experiments confirm that the proposed method can accurately estimate the target object in accordance with the user’s intention.

Infrared small target detection (IRSTD) remains a long challenging problem in infrared imaging technology. To enhance detection performance while more effectively exploiting target-specific characteristics, a novel U-shaped segmentation network called knowledge-embedded CSwin-UNet (KECS-Net) is proposed in this letter. KECS-Net first incorporates a CSwin transformer module into the encoder of the UNet backbone, enabling the extraction of multiscale features from infrared targets within an expanded receptive field, while achieving higher computational efficiency compared to the original Swin transformer. Besides, a multiscale local contrast enhancement module (MLCEM) is introduced, which utilizes hand-crafted dilated convolution operators to amplify locally salient target responses and suppress background noise, thereby guiding the model to focus on potential target regions. Finally, a slicing-aided hypersegmentation (SAHS) method is also designed to resize and rescale the output image, increasing the relative size of small targets and improving segmentation accuracy during inference. Extensive experiments on three benchmark datasets demonstrate that the proposed KECS-Net outperforms the state-of-the-art (SOTA) methods in both quantitative metrics and visual quality. Relevant code will be available at https://github.com/Lilingxiao-image/KECS-Net

In this paper, we propose a novel control scheme for a vision-based prosthetic hand. To realize complex and flexible human-like hand movements, the proposed method fuses bimodal information. Combining information from surface EMG signals with object information from a vision sensor, the system can select an appropriate hand motion. The training/recognition using both sEMG signals and object images can be performed with a single deep neural network in an end-to-end manner. The bimodal sensor information enables the system to recognize the operator's intended motion with higher accuracy than that of the conventional method using only sEMG signals. In addition, the generalization ability of the network is improved, so motion recognition robustness is enhanced against abnormal data that include partly noisy or missing samples. To verify the validity of the proposed approach, we prepared a dataset that contains the sEMG signals and the object images for 10 types of grasping motions. Three kinds of experiments were conducted: comparison of the proposed method with the conventional method, examination of the recognition robustness against partly noisy or missing samples, and challenges to recognize hand motions based on raw sEMG signals. The results revealed that the proposed bimodal network achieved considerably high recognition performance.

This paper proposes a novel prosthetic hand control method that incorporates spatial information of target objects obtained with a RGB-D sensor into a myoelectric control procedure. The RGB-D sensor provides not only two-dimensional (2D) color information but also depth information as spatial cues on target objects, and these pieces of information are used to classify objects in terms of shape features. The shape features are then used to determine an appropriate grasp strategy/motion for control of a prosthetic hand. This paper uses a two-channel image format for classification, which contains grayscale and depth information of objects, and the image data is classified with a deep convolutional neural network (DCNN). Compared with previous studies based only on 2D color images, it is expected that the spatial information would improve classification accuracy, and consequently better grasping decision and prosthetic control can be achieved. In this study, a dataset of image pairs, consisting of grayscale images and their corresponding depth images, has been created to validate the proposed method. This database includes images of simple three-dimensional (3D) solid objects from six categories, namely, triangular prism, triangular pyramid, quadrangular prism, rectangular pyramid, cone, and cylinder. Image classification experiments were conducted with this database. The experimental results indicate that spatial information possesses high potential in classifying shape features of objects.