Article
Computer Science, Information Systems
Zhihong Yu, Yunpeng Ma, Yaqin Zhou, Chunkuan Wang, Qingwu Li
Summary: In this paper, a binocular stereo visual servo system is developed to detect, locate and repel birds in substations in real-time. The system can meet the real-time and accuracy requirements of detecting, locating and repelling birds in practical substation application.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Zimiao Zhang, Hao Zhang, Kai Xu, Yanan Wu, Fumin Zhang
Summary: This paper presents a non-iterative calibration method for the extrinsic parameters of binocular stereo vision system considering the line constraints of a planar target. By adding additional equations and utilizing the line constraints formed by calibration points, the accuracy and stability of measurements can be improved.
Article
Business
Kevin L. Sample, John Hulland, Julio Sevilla, Lauren I. Labrecque
Summary: This research combines marketing literature, design theory, interviews with famous designers, and scale development procedures to create a reliable and valid tool for measuring the effectiveness of design communication. The Design Communication Assessment Scale (DCAS) developed in this study improves understanding of the evaluative dimensions of design and enables better communication between managers and designers. The generalizability of DCAS is supported by laboratory and field studies, showing improved performance across various metrics for different products.
JOURNAL OF MARKETING RESEARCH
(2023)
Article
Computer Science, Information Systems
Zhizun Xu, Maryam Haroutunian, Alan J. Murphy, Jeff Neasham, Rose Norman
Summary: This paper investigates a novel low-cost underwater visual navigation method that fuses information from inertial sensors and a sonar, allowing it to work with high accuracy in context-sparse environments.
Article
Optics
Junchao Zhu, Qi Zeng, Fangfang Han, Chang Jia, Yongxin Bian, Chenhong Wei
Summary: Binocular stereo vision is crucial for intelligent driving as it provides image and spatial information. However, environmental disturbances often lead to misalignment in binocular stereo matching, hindering accurate 3D reconstruction. This paper presents an active imaging perception and target measurement method that combines laser scanning and binocular vision. Experimental results show that the proposed method effectively matches binocular images and provides accurate three-dimensional information. The system also has potential applications in autonomous systems due to the advantages of laser line intensity feature matching.
Article
Chemistry, Multidisciplinary
Chengtao Zhu, Yau-Zen Chang
Summary: This paper proposes a simple texture-independent aggregation approach that achieves high performance in stereo matching. The approach involves matrix multiplications of two weighting matrices and a primary matching cost to generate dense disparity maps. Additionally, a multi-scale scheme is integrated to exploit the spatial distribution of textures for higher matching accuracy. The resulting hybrid approach surpasses most existing approaches in terms of efficiency and accuracy in stereo matching.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Chiang-Heng Chien, Chen-Chien James Hsu, Chiang-Ju Chien
Summary: This paper proposes a multiple master-slave FPGA architecture for an SIFT-based stereo visual odometry, which enables high reconfiguration for data throughputs among various modules. Experimental results show that 33.2 fps can be achieved using the KITTI dataset without the need for a large number of hardware resources.
Article
Ophthalmology
Guido Maiello, MiYoung Kwon
Summary: This study examined the impact of glaucomatous visual field damage on binocular disparity processing. The results showed a widespread loss of disparity sensitivity in both central and peripheral visual fields for patients with glaucoma. However, the cortical integration mechanisms appeared to be well preserved, allowing patients to make optimal use of their remaining binocular function.
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2023)
Article
Computer Science, Information Systems
Daniel S. Kaputa, Krystian A. Derhak
Summary: Low cost imaging sensors and powerful embedded computers have revolutionized computer vision. The challenge now is to reduce development time for targeting algorithms to specific hardware. This work presents the steps to use Model Based Design to simulate and target a stereo rectification and undistortion algorithm to an embedded FPGA system. The use of hardware-abstracted constructs and closed loop design techniques demonstrate the potential of Model Based Design for FPGA-based algorithm development.
Article
Chemistry, Multidisciplinary
Xuedong Jiang, Zunmin Liu, Bilong Liu, Jiang Liu
Summary: This paper proposes a lane-level location method based on multi-sensor fusion, which utilizes machine vision and binocular camera to obtain lane line information, and uses inertial navigation and odometer to obtain heading angle and distance information of the vehicle, achieving accurate lateral positioning.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Naomi A. Ubina, Shyi-Chyi Cheng, Chin-Chun Chang, Sin-Yi Cai, Hsun-Yu Lan, Hoang-Yang Lu
Summary: Precise fish metric estimation is crucial in aquaculture farm decisions. However, underwater stereo cameras face challenges in accuracy due to various factors. To address this, we propose a deep-learning-based object matching method. By using reliable convolutional neural networks for fish tracking and depth computing, accuracy can be improved.
Article
Engineering, Electrical & Electronic
Ruihang Miao, Jiuchao Qian, Yang Song, Rendong Ying, Peilin Liu
Summary: In this article, a novel underwater visual-inertial odometry (VIO) method is proposed, which combines the direct method and feature-based method. The method achieves accurate and robust odometry results through a new underwater image rectification method and a unified optimization method. The proposed system demonstrates good performance in both experimental and real underwater environments.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Robotics
Peiyu Chen, Weipeng Guan, Peng Lu
Summary: In this research, ESVIO, the first event-based stereo visual-inertial odometry system is proposed, which takes advantage of event streams, standard images, and inertial measurements. Our pipeline includes ESIO (purely event-based) and ESVIO (event with image-aided), achieving spatial and temporal associations between consecutive stereo event streams. By tightly coupling the multi-sensor measurements, a well-designed back-end is used to obtain robust state estimation. ESIO and ESVIO are validated to outperform other image-based and event-based baseline methods on public and self-collected datasets. Furthermore, real-world experiments and autonomous driving data sequences demonstrate the long-term effectiveness of our system. This work emphasizes the real-time, accurate nature of the system aimed at robust state estimation under challenging environments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Neurosciences
Adrian K. T. Ng, Ke Jia, Nuno R. Goncalves, Elisa Zamboni, Valentin G. Kemper, Rainer Goebel, Andrew E. Welchman, Zoe Kourtzi
Summary: This study utilized ultra-high-field functional imaging to examine the fine-scale processing of BOLD fMRI signals involved in 3D perception, revealing depth-specific representations in areas V3A and V7, as well as higher feedforward connectivity for correlated stimuli between these areas. Additionally, disparity-specific feedback signals were observed from V3A to V1 and from V7 to V3A, providing evidence for the role of V3A as a key nexus for disparity processing related to the perceptual estimation of 3D structures.
JOURNAL OF NEUROSCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Liping Yu, Nurlat Bekdullayev, Gilles Lubineau
Summary: A smartphone-based stereo-DIC system with a 3D-printed four-mirror adapter was proposed as a cost-effective tool for 3D displacements measurement, but was found to be sensitive to temperature variations. Comprehensive thermal error analysis revealed that thermal errors were mainly caused by the adapter rather than internal deformation of the smartphone camera, leading to the fabrication of a modified adapter with reduced sensitivity to temperature variations.
IEEE SENSORS JOURNAL
(2021)
Article
Agriculture, Multidisciplinary
Longsheng Fu, Yali Feng, Jingzhu Wu, Zhihao Liu, Fangfang Gao, Yaqoob Majeed, Ahmad Al-Mallahi, Qin Zhang, Rui Li, Yongjie Cui
Summary: Automatic detection of kiwifruit in the orchard is challenging due to varying illumination and color similarity with the complex background. A deep YOLOv3-tiny model (DY3TNet) was developed for efficient and accurate detection, achieving high precision and fast processing speed, especially in images captured with flash.
PRECISION AGRICULTURE
(2021)
Article
Robotics
Yaqoob Majeed, Manoj Karkee, Qin Zhang, Longsheng Fu, Matthew D. Whiting
Summary: The study introduced a machine vision-based system and integrated green shoot thinning system for accurately estimating vine cordon trajectories and automatically positioning the thinning end-effector. Field evaluations showed that the integrated system can achieve an RMSE of 1.47 cm in following the cordon trajectories at 6.6 cm/s forward speed. Future work will focus on incorporating additional sensing systems to achieve a higher level of precision in green shoot thinning.
JOURNAL OF FIELD ROBOTICS
(2021)
Article
Engineering, Chemical
Veronique Gomes, Marco S. Reis, Francisco Rovira-Mas, Ana Mendes-Ferreira, Pedro Melo-Pinto
Summary: The high quality of Port wine is achieved through a series of winemaking operations, with the sugar content of grapes during harvesting playing a key role. Using hyperspectral imaging technology and machine learning algorithms, predictions of sugar levels are made to establish harvest dates and select the best grapes. Among four machine learning methods, convolutional neural networks were found to outperform others in predicting sugar content from hyperspectral data.
Article
Energy & Fuels
Ryo Arai, Satoru Sakai, Akihiro Tatsuoka, Qin Zhang
Summary: This paper discusses the importance of energy behaviors in hydraulic cylinder dynamics for model-based control of agriculture scale excavators. The author constructs a nominal numerical simulator based on experimental data and analyzes energy behaviors from the port-Hamiltonian point of view. The study shows that the port-Hamiltonian perspective is applicable in agriculture scale despite modeling errors.
Article
Agronomy
Zheng Zhou, Geraldine Diverres, Chenchen Kang, Sushma Thapa, Manoj Karkee, Qin Zhang, Markus Keller
Summary: This study proposes a robust strategy to assess crop water status in grapevines by using thermal and RGB images to calculate crop water stress index (CWSI) and correlating it with leaf water potential (psi(leaf)). The results demonstrate that the proposed algorithm can be used for real-time assessment of crop water status in commercial vineyards and decision support systems for grapevine irrigation management.
Article
Agriculture, Multidisciplinary
Fangfang Gao, Wentai Fang, Xiaoming Sun, Zhenchao Wu, Guanao Zhao, Guo Li, Rui Li, Longsheng Fu, Qin Zhang
Summary: This study develops an automated video processing method to improve the counting accuracy of apple fruits in orchard environment. By tracking the trunk instead of the fruits, a higher accuracy and speed can be achieved. The method combines YOLOv4-tiny network and CSR-DCF algorithm for training and utilizes frame displacement to predict fruit locations. Results show a high counting accuracy in orchard videos.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Agriculture, Multidisciplinary
Santosh Bhusal, Manoj Karkee, Uddhav Bhattarai, Yaqoob Majeed, Qin Zhang
Summary: This study investigates the automation of a UAV-based bird deterrence system for agricultural fields. By optimizing the machine vision system, dynamically creating intelligent UAV missions, and executing tasks independently or jointly, the system achieved a successful completion rate of around 90%. However, the system still has shortcomings due to the lack of GPS navigation.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Chemistry, Analytical
Enrique Orti, Andres Cuenca, Montano Perez, Antonio Torregrosa, Coral Ortiz, Francisco Rovira-Mas
Summary: This study evaluated the performance of a commercial blast sprayer modified with pulse-width-modulated nozzles under laboratory conditions. The results showed that the nozzles were capable of modulating flow rate according to the duty cycle, but the reduction of flow rates for different pressures was lower than expected.
Article
Green & Sustainable Science & Technology
Gabriela Clemente, Alberto Garcia-Prats, Purificacion Lison, Constanza Rubio, Santiago Vidal-Puig, Beatriz Ricarte, Vicente Estruch-Guitart, Loreto Fenollosa, Juan Manzano, Francisco Rovira-Mas, Maria Vargas, Alberto San Bautista
Summary: This study examines the impact of the COVID-19 crisis on the academic performance of students at the School of Agricultural Engineering and Environment at the Universitat Politecnica de Valencia (Spain). The results indicate a positive effect on student grades during the emergency remote teaching period in 2019-2020. The study also surveys instructors and students to identify challenges and proposes measures to enhance distance learning in engineering colleges.
Review
Agriculture, Multidisciplinary
Qinghua Yang, Xiaoqiang Du, Zhiheng Wang, Zhichao Meng, Zenghong Ma, Qin Zhang
Summary: This article provides a systematic overview of recent achievements in agricultural robotic technologies for crop production. It focuses on three core aspects: mobile platforms and in-field navigation technologies; actuation mechanisms and end-effector technologies; and target detection and operation planning technologies. The article also briefly introduces successful robotic solutions for various field operations, such as transplanting, weeding, harvesting, and pruning.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Agronomy
Veronica Saiz-Rubio, Coral Ortiz, Antonio Torregrosa, Enrique Orti, Montano Perez, Andres Cuenca, Francisco Rovira-Mas
Summary: The flowrate control of spraying systems with pulse-width-modulated solenoid valves is well applied in commodity crops, but less developed for fruit trees in orchards that require higher pressures. This study compared preset duty cycles with actual ones estimated from measuring flowrates for an air-assisted orchard sprayer. The results showed deviations in transitional periods and a proposed correction model to ensure precise spray flowrate.
Article
Horticulture
Coral Ortiz, Antonio Torregrosa, Veronica Saiz-Rubio, Francisco Rovira-Mas
Summary: Spraying systems are necessary to protect crops and maintain food production, but precision agriculture is crucial to reduce negative effects of pesticides. This paper analyzes vibrations induced in a vineyard sprayer controlled by pulse-width-modulated nozzles, focusing on the instantaneous duty cycle as the control variable. The study confirms the difficulty of achieving accurate duty cycles in smart sprayers and highlights the importance of understanding the vibration effects of pulses.
Editorial Material
Agriculture, Multidisciplinary
Qin Zhang
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Proceedings Paper
Automation & Control Systems
Zixuan He, Manoj Karkee, Qin Zhang
Summary: Automated or robotic harvesting methods are being investigated as alternatives to manual harvesting in strawberry production. This study focused on detecting and estimating the location of strawberries using machine vision systems. The use of YOLOv4 and YOLOv4-tiny models achieved high precision in detecting and estimating strawberry centers in field conditions.
Article
Robotics
Xin Zhang, Manoj Karkee, Qin Zhang, Matthew D. Whiting
Summary: Fresh market apples in the United States, mainly produced in Washington, face challenges due to uncertain seasonal labor. Automated harvesting solutions are being developed using computer vision and convolutional neural networks to identify tree branches and trunks for precise end-effector positioning. ResNet-18 has shown superior performance in identification accuracy compared to VGGs, aiding in the success of automated shaking points determination.
JOURNAL OF FIELD ROBOTICS
(2021)
Article
Agricultural Engineering
Yifan Bai, Junzhen Yu, Shuqin Yang, Jifeng Ning
Summary: A real-time recognition algorithm (Improved YOLO) is proposed in this paper for accurately identifying small, similar-colored, and overlapping strawberry seedling flowers and fruits. The experimental results show that the algorithm achieves high precision, recall, and average precision, and meets the real-time detection requirements, providing effective support for the automated management of strawberry seedling flower and fruit thinning.
BIOSYSTEMS ENGINEERING
(2024)