Search results

The purpose of this paper is to develop an integrated, computer vision-based system to operate a commercial wheelchair-mounted robotic manipulator (WMRM). In addition, a gesture recognition interface system was developed specially for individuals with upper-level spinal cord injuries including object tracking and face recognition to function as an efficient, hands-free WMRM controller.

Two Kinect® cameras were used synergistically to perform a variety of simple object retrieval tasks. One camera was used to interpret the hand gestures and locate the operator's face for object positioning, and then send those as commands to control the WMRM. The other sensor was used to automatically recognize different daily living objects selected by the subjects. An object recognition module employing the Speeded Up Robust Features algorithm was implemented and recognition results were sent as a commands for “coarse positioning” of the robotic arm near the selected object. Automatic face detection was provided as a shortcut enabling the positing of the objects close by the subject's face.

The gesture recognition interface incorporated hand detection, tracking and recognition algorithms, and yielded a recognition accuracy of 97.5 percent for an eight-gesture lexicon. Tasks’ completion time were conducted to compare manual (gestures only) and semi-manual (gestures, automatic face detection, and object recognition) WMRM control modes. The use of automatic face and object detection significantly reduced the completion times for retrieving a variety of daily living objects.

Integration of three computer vision modules were used to construct an effective and hand-free interface for individuals with upper-limb mobility impairments to control a WMRM.

A fine‐grained video content indexing, retrieval, and adaptation requires accurate metadata describing the video structure and semantics to the lowest granularity, i.e. to the object level. The authors address these requirements by proposing semantic video content annotation tool (SVCAT) for structural and high‐level semantic video annotation. SVCAT is a semi‐automatic MPEG‐7 standard compliant annotation tool, which produces metadata according to a new object‐based video content model introduced in this work. Videos are temporally segmented into shots and shots level concepts are detected automatically using ImageNet as background knowledge. These concepts are used as a guide to easily locate and select objects of interest which are then tracked automatically to generate an object level metadata. The integration of shot based concept detection with object localization and tracking drastically alleviates the task of an annotator. The paper aims to discuss these issues.

A systematic keyframes classification into ImageNet categories is used as the basis for automatic concept detection in temporal units. This is then followed by an object tracking algorithm to get exact spatial information about objects.

Experimental results showed that SVCAT is able to provide accurate object level video metadata.

The new contribution in this paper introduces an approach of using ImageNet to get shot level annotations automatically. This approach assists video annotators significantly by minimizing the effort required to locate salient objects in the video.

This study aims to introduce a new methodology for generating synthetic images for facility management purposes. The method starts by leveraging the existing 3D open-source BIM models and using them inside a graphic engine to produce a photorealistic representation of indoor spaces enriched with facility-related objects. The virtual environment creates several images by changing lighting conditions, camera poses or material. Moreover, the created images are labeled and ready to be trained in the model.

This paper focuses on the challenges characterizing object detection models to enrich digital twins with facility management-related information. The automatic detection of small objects, such as sockets, power plugs, etc., requires big, labeled data sets that are costly and time-consuming to create. This study proposes a solution based on existing 3D BIM models to produce quick and automatically labeled synthetic images.

The paper presents a conceptual model for creating synthetic images to increase the performance in training object detection models for facility management. The results show that virtually generated images, rather than an alternative to real images, are a powerful tool for integrating existing data sets. In other words, while a base of real images is still needed, introducing synthetic images helps augment the model’s performance and robustness in covering different types of objects.

This study introduced the first pipeline for creating synthetic images for facility management. Moreover, this paper validates this pipeline by proposing a case study where the performance of object detection models trained on real data or a combination of real and synthetic images are compared.

This paper aims to present an object detection methodology to categorize 3D object models in an efficient manner. The authors propose a dynamically generated hierarchical architecture to compute very fast objects’ 3D pose for mobile service robots to grasp them.

The methodology used in this study is based on a dynamic pyramid search and fast template representation, metadata and context-free grammars. In the experiments, the authors use an omnidirectional KUKA mobile manipulator equipped with an RGBD camera, to localize objects requested by humans. The proposed architecture is based on efficient object detection and visual servoing. In the experiments, the robot successfully finds 3D poses. The present proposal is not restricted to specific robots or objects and can grow as much as needed.

The authors present the dynamic categorization using context-free grammars and 3D object detection, and through several experiments, the authors perform a proof of concept. The authors obtained promising results, showing that their methods can scale to more complex scenes and they can be used in future applications in real-world scenarios where mobile robot are needed in areas such as service robots or industry in general.

The experiments were carried out using a mobile KUKA youBot. Scalability and more robust algorithms will improve the present proposal. In the first stage, the authors carried out an experimental validation.

The current proposal describes a scalable architecture, where more agents can be added or reprogrammed to handle more complicated tasks.

The main contribution of this study resides in the dynamic categorization scheme for fast detection of 3D objects, and the issues and experiments carried out to test the viability of the methods. Usually, state-of-the-art treats categories as rigid and make static queries to datasets. In the present approach, there are no fixed categories and they are created and combined on the fly to speed up detection.

Monitoring of the quality of precast concrete (PC) components is crucial for the success of prefabricated construction projects. Currently, quality monitoring of PC components during the construction phase is predominantly done manually, resulting in low efficiency and hindering the progress of intelligent construction. This paper presents an intelligent inspection method for assessing the appearance quality of PC components, utilizing an enhanced you look only once (YOLO) model and multi-source data. The aim of this research is to achieve automated management of the appearance quality of precast components in the prefabricated construction process through digital means.

The paper begins by establishing an improved YOLO model and an image dataset for evaluating appearance quality. Through object detection in the images, a preliminary and efficient assessment of the precast components' appearance quality is achieved. Moreover, the detection results are mapped onto the point cloud for high-precision quality inspection. In the case of precast components with quality defects, precise quality inspection is conducted by combining the three-dimensional model data obtained from forward design conversion with the captured point cloud data through registration. Additionally, the paper proposes a framework for an automated inspection platform dedicated to assessing appearance quality in prefabricated buildings, encompassing the platform's hardware network.

The improved YOLO model achieved a best mean average precision of 85.02% on the VOC2007 dataset, surpassing the performance of most similar models. After targeted training, the model exhibits excellent recognition capabilities for the four common appearance quality defects. When mapped onto the point cloud, the accuracy of quality inspection based on point cloud data and forward design is within 0.1 mm. The appearance quality inspection platform enables feedback and optimization of quality issues.

The proposed method in this study enables high-precision, visualized and automated detection of the appearance quality of PC components. It effectively meets the demand for quality inspection of precast components on construction sites of prefabricated buildings, providing technological support for the development of intelligent construction. The design of the appearance quality inspection platform's logic and framework facilitates the integration of the method, laying the foundation for efficient quality management in the future.

Scattered parts are laid randomly during the manufacturing process and have difficulty to recognize and manipulate. This study aims to complete the grasp of the scattered parts by a manipulator with a camera and learning method.

In this paper, a cascaded convolutional neural network (CNN) method for robotic grasping based on monocular vision and small data set of scattered parts is proposed. This method can be divided into three steps: object detection, monocular depth estimation and keypoint estimation. In the first stage, an object detection network is improved to effectively locate the candidate parts. Then, it contains a neural network structure and corresponding training method to learn and reason high-resolution input images to obtain depth estimation. The keypoint estimation in the third step is expressed as a cumulative form of multi-scale prediction from a network to use an red green blue depth (RGBD) map that is acquired from the object detection and depth map estimation. Finally, a grasping strategy is studied to achieve successful and continuous grasping. In the experiments, different workpieces are used to validate the proposed method. The best grasping success rate is more than 80%.

By using the CNN-based method to extract the key points of the scattered parts and calculating the possibility of grasp, the successful rate is increased.

This method and robotic systems can be used in picking and placing of most industrial automatic manufacturing or assembly processes.

Unlike standard parts, scattered parts are randomly laid and have difficulty recognizing and grasping for the robot. This study uses a cascaded CNN network to extract the keypoints of the scattered parts, which are also labeled with the possibility of successful grasping. Experiments are conducted to demonstrate the grasping of those scattered parts.

During the past decades, several researchers have introduced devices that use sonar systems to detect and/or to determine the object location or to measure the distance to an object using reflected sound waves. The purpose of this paper is to use sonar sensor with textile structure and to test it for detection of objects.

In this study, a sonar system based on intelligent textiles approach for detection of objects has been developed. In order to do this, ultrasonic sensor has been integrated to textile structures by using conductive yarns. Furthermore, an electronic circuit has been designed; PIC 16F877 microcontroller unit has been used to convert the measured signal to meaningful data and to assess the data. The algorithm enabling the objects detection has also been developed. Finally, smart textile structure integrated with ultrasonic sensor has been tested for detection of objects.

Beam shape is presented related to identified object and compared with the actual one given in sensor's datasheet in order to test the efficiency of the proposed method of detection. The achieved results showed that the determined beam pattern matches with the actual one given in its datasheet. Therefore, it can be concluded that the integration of sensor was successful.

This is the first time in the literature that a sonar sensor was integrated into textile structure and tested for detection of objects.

Geographical conditions monitoring (GCM) has elicited significant concerns from the Chinese Government and is closely related to the “Digital China” program. This research aims to focus on object-based change detection (OBCD) methods integrating very-high-resolution (VHR) imagery and vector data for GCM.

The main content of this paper is as follows: a multi-resolution segmentation (MRS) algorithm is proposed for obtaining homogeneous and contiguous image objects in two phases; a post-classification comparison (PCC) method based on the nearest neighbor algorithm and an image-object analysis (IOA) technique based on a differential entropy algorithm are used to improve the accuracy of the change detection; and a vector object-based accuracy assessment method is proposed.

Results show that image objects obtained using the MRS algorithm attain the objectives of the “same spectrum within classes” and “different spectrum among classes”. Moreover, the two OBCD methods can detect over 85 per cent of the changed regions. The PCC strategy can obtain the categories of image objects with a high degree of precision. The IOA technique is easy to use and largely automated.

On the basis of the VHR satellite imagery and vector data, the above methods can effectively and accurately provide technical support for GCM implementation.

The purpose of this paper is to describe simulation research carried out for the needs of multi-sensor anti-collision system for light aircraft and unmanned aerial vehicles.

This paper presents an analysis related to the practical possibilities of detecting intruders in the air space with the use of optoelectronic sensors. The theoretical part determines the influence of the angle of view, distance from the intruder and the resolution of the camera on the ability to detect objects with different linear dimensions. It has been assumed that the detection will be effective for objects represented by at least four pixels (arranged in a line) on the sensor matrix. In the main part devoted to simulation studies, the theoretical data was compared to the obtained intruders’ images. The verified simulation environment was then applied to the image processing algorithms developed for the anti-collision system.

A simulation environment was obtained enabling reliable tests of the anti-collision system using optoelectronic sensors.

The integration of unmanned aircraft operations in civil airspace is a serious problem on a global scale. Equipping aircraft with autonomous anti-collision systems can help solve key problems. The use of simulation techniques in the process of testing anti-collision systems allows the implementation of test scenarios that may be burdened with too much risk in real flights.

This paper aims for possible improvement of safety in light-sport aviation.

This paper conducts verification of classic flight simulator software suitability for carrying out anti-collision systems tests and development of a flight simulator platform dedicated to such tests.

The real-time generation of feature descriptors for object recognition is a challenging problem. In this research, the purpose of this paper is to provide a hardware friendly framework to generate sparse features that can be useful for key feature point selection, feature extraction, and descriptor construction. The inspiration is drawn from feature formation processes of the human brain, taking into account the sparse, modular, and hierarchical processing of visual information.

A sparse set of neurons referred as active neurons determines the feature points necessary for high-level vision applications such as object recognition. A psycho-physical mechanism of human low-level vision relates edge detection to noticeable local spatial stimuli, representing this set of active neurons. A cognitive memory cell array-based implementation of low-level vision is proposed. Applications of memory cell in edge detection are used for realizing human vision inspired feature selection and leading to feature vector construction for high-level vision applications.

True parallel architecture and faster response of cognitive circuits avoid time costly and redundant feature extraction steps. Validation of proposed feature vector toward high-level computer vision applications is demonstrated using standard object recognition databases. The comparison against existing state-of-the-art object recognition features and methods shows an accuracy of 97, 95, 69 percent for Columbia Object Image Library-100, ALOI, and PASCAL VOC 2007 databases indicating an increase from benchmark methods by 5, 3 and 10 percent, respectively.

A hardware friendly low-level sparse edge feature processing system is proposed for recognizing objects. The edge features are developed based on threshold logic of neurons, and the sparse selection of the features applies a modular and hierarchical processing inspired from the human neural system.