Object manipulation with a variable-stiffness robotic mechanism using deep neural networks for visual semantics and load estimation

Brain-machine interface systems (BMI) have allowed the control of prosthetics and robotic arms using brainwaves alone to do simple tasks such as grasping an object. However, the low throughput information of brain-data decoding does not allow the robotic arm to achieve diverse grasp configurations for different types of objects. On the other hand, computer vision researchers have mostly solved the problem of robot hand configuration for object-grasping given visual object recognition. It is then natural to think that if the robotic arm could decode from brain data the image of the object that the user intends to grasp, then it could automatically decide the type of grasping to execute. For this reason, in this paper, we propose a method to decode visual representations of objects from brain data towards improving robot arm grasp configurations. More specifically, we recorded EEG data during an object-grasping experiment in which the participant had to control a robotic arm using a BMI to grasp an object. We also recorded images of the object and developed a multimodal representation of the encoded brain data and object image. Given this representation, the objective was to reconstruct the image given that only half of the image (the brain data encoding) was provided. To achieve this goal, we developed a deep convolutional autoencoder that learned a noise-free joint manifold of brain data encoding and the object image. After training, the autoencoder was able to reconstruct the missing part of the object image given that only brain data encoding was provided.

Deep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications.

A cellular array algorithm is presented which allows the manipulation of objects across a distributed manipulator array. Objects are placed on the manipulator array surface and the algorithm differentiates between two different types of objects depending on their physical properties. The different objects are then controlled by the algorithm and the manipulator array so that the objects end up grouped together in different regions of the manipulator array. The algorithm has been verified using a physics-based 3D simulation engine.

Brain-computer interface (BCI) has great potential to replace lost upper limb function. Thus, there has been great interest in the development of BCI-controlled robotic arm. However, few studies have attempted to use noninvasive electroencephalography (EEG)-based BCI to achieve high-level control of a robotic arm. In this paper, a high-level control architecture combining augmented reality (AR) BCI and computer vision was designed to control a robotic arm for performing a pick and place task. A steady-state visual evoked potential (SSVEP)-based BCI paradigm was adopted to realize the BCI system. Microsoft's HoloLens was used to build an AR environment and served as the visual stimulator for eliciting SSVEPs. The proposed AR-BCI was used to select the objects that need to be operated by the robotic arm. The computer vision was responsible for providing the location, color and shape information of the objects. According to the outputs of the AR-BCI and computer vision, the robotic arm could autonomously pick the object and place it to specific location. Online results of 11 healthy subjects showed that the average classification accuracy of the proposed system was 91.41%. These results verified the feasibility of combing AR, BCI and computer vision to control a robotic arm, and are expected to provide new ideas for innovative robotic arm control approaches.

InceptB: A CNN Based Classification Approach for Recognizing Traditional Bengali Games

PurposeThe growth of police operated surveillance cameras has out-paced the ability of humans to monitor them effectively. Computer vision is a possible solution. An ongoing research project on the application of computer vision within a municipal police department is described. The paper aims to discuss these issues.Design/methodology/approachFollowing the demystification of computer vision technology, its potential for police agencies is developed within a focus on computer vision as a solution for two common surveillance camera tasks (live monitoring of multiple surveillance cameras and summarizing archived video files). Three unaddressed research questions (can specialized computer vision applications for law enforcement be developed at this time, how will computer vision be utilized within existing public safety camera monitoring rooms, and what are the system-wide impacts of a computer vision capability on local criminal justice systems) are considered.FindingsDespite computer vision becoming accessible to law enforcement agencies the impact of computer vision has not been discussed or adequately researched. There is little knowledge of computer vision or its potential in the field.Originality/valueThis paper introduces and discusses computer vision from a law enforcement perspective and will be valuable to police personnel tasked with monitoring large camera networks and considering computer vision as a system upgrade.

Deformable models are a useful tool in computer vision and computer graphics. A deformable model is a curve (in two dimensions) or a surface (in three dimensions), whose shape, position, and orientation are controlled through a set of parameters. Deformable models can represent manufactured objects, human faces and skeletons, and even bodies of fluid. In computer graphics, we use deformable models for animations and simulations, whereas in computer vision applications, such as tracking and fitting, deformable models help to restrict the family of possible solutions. We introduce the use of a directed acyclic graph (DAG) to describe the position and Jacobian of each point on the surface of deformable models. This data structure, combined with a topological description of the points, is simple, powerful, and extremely useful for both computer vision and computer graphics applications. We show a computer vision application, 3D deformable face tracking, and a computer graphics application, cyberglove data visualization and calibration.

Labour productivity is a crucial factor in the success of construction projects. However, Sri Lankan construction industry has been struggling to enhance labour productivity due to inadequate labour management, poor monitoring systems and safety-related problems. These various challenges have led to problems such as project delays and cost overruns, and poor site performance. Computer vision (CV) has been found to overcome these issues and enhance labour management in the construction industry. Additionally, CV can monitor the activities of labours, track activities, control behaviour, detect the location and identify objects continuously, which ultimately enhances the labour productivity. By automating data collection through cameras and AI models, site managers gain accurate insights into performance without disrupting workflows. It ensures transparency, accountability, and quick response to inefficiencies. This research study focuses on deploying CV to improve labour productivity in the Sri Lankan construction industry. This study was based on information gathered from 16 expert interviews involving construction professionals and IT specialists. The findings highlight CV applications in labour management and further present substantial possibilities to transform the construction industry through CV. Moreover, the study highlights real-time monitoring together with task optimization, safety improvement and workforce efficiency enhancement. Finally, this research provides CV applications and key stages as follows with a view to indicating appropriate decisions to make. Application of CV can assist in avoiding problems and identifying the best practices in the application of CV technologies in the Sri Lankan construction industry.

In this paper, a low-cost, 3D printed robotic arm that uses a system of gesture recognition controlled via computer vision is presented. The developed approach of Human-Computer Interaction (HCI) employs a single commonly available USB2.0 High-Definition camera to capture hand movements and gestures, implementing the OpenCV library. This enables the translation of those movements and gestures into commands that can be transferred using internet protocols to a Raspberry Pi; then interfaces with the robotic arm. Using computer vision as a method of HCI reduces components and overall cost. The Raspberry Pi uses individual commands to control the robotic arm's servo motors while monitoring multiple pressure sensors and limit switches to ensure the robotic arm operates within a certain limit of load. This prevents the arm from overextending itself while protecting the integrity of items within its grasp.

Artificial Intelligence in the American Healthcare Industry: Looking Forward to 2030

Computer vision is one of the hottest research fields in deep learning. The emergence of generative adversarial networks (GANs) provides a new method and model for computer vision. The idea of GANs using the game training method is superior to traditional machine learning algorithms in terms of feature learning and image generation. GANs are widely used not only in image generation and style transfer but also in the text, voice, video processing, and other fields. However, there are still some problems with GANs, such as model collapse and uncontrollable training. This paper deeply reviews the theoretical basis of GANs and surveys some recently developed GAN models, in comparison with traditional GAN models. The applications of GANs in computer vision include data enhancement, domain transfer, high-quality sample generation, and image restoration. The latest research progress of GANs in artificial intelligence (AI) based security attack and defense is introduced. The future development of GANs in computer vision is also discussed at the end of the paper with possible applications of AI in computer vision.

Crop type mapping by using transfer learning

Convolutional neural networks (CNN) are widely used in computer vision, especially in image classification. However, the way in which information and invariance properties are encoded through in deep CNN architectures is still an open question. In this paper, we propose to modify the standard convolutional block of CNN in order to transfer more information layer after layer while keeping some invariance within the network. Our main idea is to exploit both positive and negative high scores obtained in the convolution maps. This behavior is obtained by modifying the traditional activation function step before pooling. We are doubling the maps with specific activations functions, called MaxMin strategy, in order to achieve our pipeline. Extensive experiments on two classical datasets, MNIST and CIFAR-10, show that our deep MaxMin convolutional net outperforms standard CNN.

The recognition of image text sequences has been the subject of long-term research in computer vision. The recognition problem of the shell number image sequence studied in this paper is based on the deep convolutional neural network architecture, and an image recognition algorithm that integrates feature extraction, sequence modeling, and transcription into a unified framework is adopted. The algorithm used has four characteristics: (1) Compared with most algorithms that require separate training and coordination, the method adopted in this paper has end-to-end characteristics. (2) It can handle indefinite length image sequences without involving character segmentation or horizontal-scale normalization. (3) The algorithm is not limited to any predefined vocabulary, and has achieved remarkable performance in both no-lexicon and dictionary-based scene text recognition tasks. (4) The algorithm produces an efficient and much smaller model, which is more practical for real-world scenarios. Using this algorithm for bay number recognition can assist in scene location and provide smart services and application through AI technology.

We have presented the newly developed anthropomorphic robot hand named the KH Hand type S and its master slave system using the bilateral controller. The use of an elastic body has improved the robot hand in terms of weight, the backlash of the transmission, and friction between the gears. We have demonstrated the expression of the Japanese finger alphabet. We have also shown an experiment of a peg-in-hole task controlled by the bilateral controller. These results indicate that the KH Hand type S has a higher potential than previous robot hands in performing not only hand shape display tasks but also in grasping and manipulating objects in a manner like that of the human hand. In our future work, we are planning to study dexterous grasping and manipulation by the robot.