The equipment detection and localization of large-scale construction jobsite by far-field construction surveillance video based on improving YOLOv3 and grey wolf optimizer improving extreme learning machine

Zeng, Tuocheng; Wang, Jiajun; Cui, Bo; Wang, Xiaoling; Wang, Dong; Zhang, Yunuo

doi:10.1016/j.conbuildmat.2021.123268

Cited by 19 publications

(9 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of GWO and its variants enables it to successfully tackle a wide range of real-world applications. This include electrical and electronic engineering [147], [148], [185], renewable energy [226], [181], [195], networking and communication [214], [186], mechanical engineering [220], [130], medical applications [227], [67], classification [228], [157], [229], [173], [85], chemical engineering [230], [231], petroleum engineering [129], [215], industrial engineering [232], [219], software engineering [65], civil engineering [233], [234], geotechnical & geoenvironmental Engineering [235], [236], planing & scheduling [170], [110], robotics [237], [127], image processing [238], [239], [240], and mathematical functions [123], [241], and others [242], [243], [244].…”

Section: Applications Of Grey Wolf Optimizermentioning

confidence: 99%

“…In the same way, the GWO-based algorithms are applied for solving optimization problems in the civil engineering domains, like control of the nonlinear building using an optimum inverse Takagi-Sugeno-Kang model of magnetorheological damper [271], predicting the compressive strength of normal and High-Performance Concretes [233], the equipment detection and localization of large-scale construction Jobsite by far-field construction surveillance video [234], estimation of soil moisture content using a dataset from Dehgolan plain -Iran [68], predicting the dynamic modulus of asphalt mixture [272], optimization of construction duration and schedule robustness [273], and predict the compressive strength of concrete with partial replacements for cement [274].…”

Section: Applications Of Grey Wolf Optimizermentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review

et al. 2024

View full text Add to dashboard Cite

The Grey Wolf Optimizer (GWO) has emerged as one of the most captivating swarm intelligence methods, drawing inspiration from the hunting behavior of wolf packs. GWO's appeal lies in its remarkable characteristics: it is parameter-free, derivative-free, conceptually simple, user-friendly, adaptable, flexible, and robust. Its efficacy has been demonstrated across a wide range of optimization problems in diverse domains, including engineering, bioinformatics, biomedical, scheduling and planning, and business. Given the substantial growth and effectiveness of GWO, it is essential to conduct a recent review to provide updated insights. This review delves into the GWO-related research conducted between 2019 and 2022, encompassing over 200 research articles. It explores the growth of GWO in terms of publications, citations, and the domains that leverage its potential. The review thoroughly examines the latest versions of GWO, categorizing them based on their contributions. Additionally, it highlights the primary applications of GWO, with computer science and engineering emerging as the dominant research domains. A critical analysis of the accomplishments and limitations of GWO is presented, offering valuable insights. Finally, the review concludes with a brief summary and outlines potential future developments in GWO theory and applications. Researchers seeking to employ GWO as a problem-solving tool will find this comprehensive review immensely beneficial in advancing their research endeavors.

show abstract

Section: Applications Of Grey Wolf Optimizermentioning

confidence: 99%

Section: Applications Of Grey Wolf Optimizermentioning

confidence: 99%

Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review

et al. 2024

View full text Add to dashboard Cite

show abstract

“…In addition, 3D localization can be achieved using cameras installed in high positions, which are generally referred to as far-field surveillance cameras, the most common type of camera on construction sites. The term far-field cameras was used in [ 40 , 41 , 42 ] to describe these cameras. Ref.…”

Section: Related Workmentioning

confidence: 99%

“…In general, the challenge of localization based on monocular vision lies in obtaining the extrinsic parameters of the camera. Therefore, most of the studies have focused on localization on construction ground planes [ 42 , 43 , 44 , 45 , 46 ], where it is convenient to perform perspective transformation and estimate the proximity of objects in three-dimensional space through two-dimensional pixel coordinates. In contrast, there is relatively less research on the 3D localization of objects in higher positions.…”

Section: Related Workmentioning

confidence: 99%

Vision-Based Automated Recognition and 3D Localization Framework for Tower Cranes Using Far-Field Cameras

Wang

Zhang

Yang

et al. 2023

Sensors

View full text Add to dashboard Cite

Tower cranes can cover most of the area of a construction site, which brings significant safety risks, including potential collisions with other entities. To address these issues, it is necessary to obtain accurate and real-time information on the orientation and location of tower cranes and hooks. As a non-invasive sensing method, computer vision-based (CVB) technology is widely applied on construction sites for object detection and three-dimensional (3D) localization. However, most existing methods mainly address the localization on the construction ground plane or rely on specific viewpoints and positions. To address these issues, this study proposes a framework for the real-time recognition and localization of tower cranes and hooks using monocular far-field cameras. The framework consists of four steps: far-field camera autocalibration using feature matching and horizon-line detection, deep learning-based segmentation of tower cranes, geometric feature reconstruction of tower cranes, and 3D localization estimation. The pose estimation of tower cranes using monocular far-field cameras with arbitrary views is the main contribution of this paper. To evaluate the proposed framework, a series of comprehensive experiments were conducted on construction sites in different scenarios and compared with ground-truth data obtained by sensors. The experimental results show that the proposed framework achieves high precision in both crane jib orientation estimation and hook position estimation, thereby contributing to the development of safety management and productivity analysis.

show abstract

“…In 2019, Duan et al proposed the CenterNet algorithm [24], which is capable of directly outputting the coordinates of the target's center point, as well as its width and height information, without the need for methods such as bounding box regression to determine the target's position. In 2021, the improved YOLOv3 model proposed by Zeng et al made full use of the shallow network by additionally eliciting the feature maps of this layer after the second downsampling and splicing them with the feature maps in the previous scale to add a scale with better detection capability of small targets and improve the detection capability of small targets [25]. In 2022, Gong et al enhanced the feature extraction and precise positioning capabilities of the YOLOv4 model by introducing techniques such as coordinate attention and deformable convolutions.…”

Section: Introductionmentioning

confidence: 99%

Real-time Detection Algorithm of Aircraft Landing Gear based on improved YOLOv8

Gao,

Chen,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

This study innovatively improves the YOLOv8 target detection model, aiming to achieve fast and accurate detection of aircraft landing gear in natural environments. By introducing a small target detection layer, a dynamic serpentine convolutional layer, and a CoTattention mechanism, the study successfully optimized the original yolov8 model to effectively detect small-sized aircraft landing gears when presented at a distance. This paper introduces a small target detection layer of 160x160 on top of the original network, significantly improving the detection performance of airplane landing gear by fusing features from different layers. Dynamic serpentine convolution uses a dynamic structure and iterative strategy to improve the model's ability to perceive complex geometric structures by optimizing the convolution kernel. The CoTAttention mechanism allows the model to consider the information of each position in the input image more comprehensively. It significantly reduces the loss of contextual information by enhancing the ability to perceive small targets. The experimental findings demonstrate a noteworthy enhancement in the performance metrics, including precision, recall, and average accuracy, when comparing the enhanced model to its original counterpart. Furthermore, the improved model effectively meets the real-time detection requirements. Compared to other object detection models, the improved model performs, offering high accuracy and real-time detection capabilities, particularly demonstrating its versatility and practical value in detecting aircraft landing gear.

show abstract

The equipment detection and localization of large-scale construction jobsite by far-field construction surveillance video based on improving YOLOv3 and grey wolf optimizer improving extreme learning machine

Cited by 19 publications

References 74 publications

Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review

Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review

Vision-Based Automated Recognition and 3D Localization Framework for Tower Cranes Using Far-Field Cameras

Real-time Detection Algorithm of Aircraft Landing Gear based on improved YOLOv8

Contact Info

Product

Resources

About