In recent years, deep learning has dominated medical image segmentation. Encoder-decoder architectures, such as U-Net, can be used in state-of-the-art models with powerful designs that are achieved by implementing skip connections that propagate local information from an encoder path to a decoder path to retrieve detailed spatial information lost by pooling operations. Despite their effectiveness for segmentation, these naïve skip connections still have some disadvantages. First, multi-scale skip connections tend to use unnecessary information and computational sources, where likable low-level encoder features are repeatedly used at multiple scales. Second, the contextual information of the low-level encoder feature is insufficient, leading to poor performance for pixel-wise recognition when concatenating with the corresponding high-level decoder feature. In this study, we propose a novel spatial-channel attention gate that addresses the limitations of plain skip connections. This can be easily integrated into an encoder-decoder network to effectively improve the performance of the image segmentation task. Comprehensive results reveal that our spatial-channel attention gate remarkably enhances the segmentation capability of the U-Net architecture with a minimal computational overhead added. The experimental results show that our proposed method outperforms the conventional deep networks in term of Dice score, which achieves 71.72%.

Using hand gestures is a natural method of interaction between humans and computers. We use gestures to express meaning and thoughts in our everyday conversations. Gesture-based interfaces are used in many applications in a variety of fields, such as smartphones, televisions (TVs), video gaming, and so on. With advancements in technology, hand gesture recognition is becoming an increasingly promising and attractive technique in human–computer interaction. In this paper, we propose a novel method for fingertip detection and hand gesture recognition in real-time using an RGB-D camera and a 3D convolution neural network (3DCNN). This system can accurately and robustly extract fingertip locations and recognize gestures in real-time. We demonstrate the accurateness and robustness of the interface by evaluating hand gesture recognition across a variety of gestures. In addition, we develop a tool to manipulate computer programs to show the possibility of using hand gesture recognition. The experimental results showed that our system has a high level of accuracy of hand gesture recognition. This is thus considered to be a good approach to a gesture-based interface for human–computer interaction by hand in the future.

This study proposes an advanced plant disease classification framework leveraging the Attention Score-Based Multi-Vision Transformer (Multi-ViT) model. The framework introduces a novel attention mechanism to dynamically prioritize relevant features from multiple leaf images, overcoming the limitations of single-leaf-based diagnoses. Building on the Vision Transformer (ViT) architecture, the Multi-ViT model aggregates diverse feature representations by combining outputs from multiple ViTs, each capturing unique visual patterns. This approach allows for a holistic analysis of spatially distributed symptoms, crucial for accurately diagnosing diseases in trees. Extensive experiments conducted on apple, grape, and tomato leaf disease datasets demonstrate the model’s superior performance, achieving over 99% accuracy and significantly improving F1 scores compared to traditional methods such as ResNet, VGG, and MobileNet. These findings underscore the effectiveness of the proposed model for precise and reliable plant disease classification.

While the demand for new high-tech technologies is rapidly increasing, difficulties are presented, such as aging and population decline in rural areas. In particular, autonomous mobile robots have been emerging in the agricultural field. Worldwide, huge investment is being made in the development of unmanned agricultural mobile robots; meanwhile with the development of robots, modern farms have high expectations of increased productivity. However, in the agricultural work environment, it is difficult to solve these problems with the existing mobile robot form, due to the difficulties of various environments. Typical problems are space constraints in the agricultural work environment, the high computational complexity of algorithms, and changes in the environment. To solve these problems, in this paper, we propose a method to design and operate a mobile robot platform that can be used in a greenhouse. We represent a robot type with two drive wheels along with four casters that can operate on path and rail. In addition, we propose a technology for a multi-AI deep learning system to operate a robot, an algorithm that can operate such a robot, and a VPN-based communication system for network and security. The proposed method is expected to increase productivity and reduce labor costs in the agricultural work environment.

A distance map captured using a time-of-flight (ToF) depth sensor has fundamental problems, such as ambiguous depth information in shiny or dark surfaces, optical noise, and mismatched boundaries. Severe depth errors exist in shiny and dark surfaces owing to excess reflection and excess absorption of light, respectively. Dealing with this problem has been a challenge due to the inherent hardware limitations of ToF, which measures the distance using the number of reflected photons. This study proposes a distance error correction method using three ToF sensors, set to different integration times to address the ambiguity in depth information. First, the three ToF depth sensors are installed horizontally at different integration times to capture distance maps at different integration times. Given the amplitude maps and error regions are estimated based on the amount of light, the estimated error regions are refined by exploiting the accurate depth information from the neighboring depth sensors that use different integration times. Moreover, we propose a new optical noise reduction filter that considers the distribution of the depth information biased toward one side. Experimental results verified that the proposed method overcomes the drawbacks of ToF cameras and provides enhanced distance maps.

Stereo matching methods have achieved remarkable improvements by exploiting various attempts. However, most stereo matching algorithms still suffer from problems such as ambiguous region and inherent ambiguities. In particular, some problems affecting cost aggregation step have the greatest impact on depth results. To resolve the above-mentioned problems, we propose a new cost aggregation method using the modified total generalized variation with fusion tensor. First, two kinds of diffusion tensors are extracted from the guidance color image and the guidance depth map. They are incorporated into an energy functional to obtain the total generalized variation. After formulating the final energy functional, it is optimized via a primal-dual energy minimization method. The performance of the proposed method is experimentally verified by qualitatively and quantitatively comparing the results to those of other algorithms.