The Bangkok Urbanscapes Dataset for Semantic Urban Scene Understanding Using Enhanced Encoder-Decoder With Atrous Depthwise Separable A1 Convolutional Neural Networks

Thitisiriwech, Kitsaphon; Panboonyuen, Teerapong; Kantavat, Pittipol; Iwahori, Yuji; Kijsirikul, Boonserm

doi:10.1109/access.2022.3176712

Cited by 10 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VGG-16 was used to classify and identify different varieties of peanuts and achieved an average accuracy of 96.7% [159]. In addition, it was utilized in the computer vision process in Unmanned Aerial Vehicles (UAV) [160] [170], detection of brain tumors in MR images [171], and urban scene analysis [172], [173]. Figure 11 shows an illustration of the algorithm utilized in approach III with Xception.…”

Section: Vgg-16mentioning

confidence: 99%

Enhanced safety implementation in 5S + 1 via object detection algorithms

Shahin

Chen

Hosseinzadeh

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Scholarly work points to 5S+1, a simple yet powerful method of initiating quality in manufacturing, as one of the foundations of Lean manufacturing and the Toyota Production Systems. The 6 th S, safety, is often used to prevent future occupational hazards, therefore, reducing the loss of time, money, and human resources. This paper aims to show how Industry 4.0 technologies such as computer-based vision and object detection algorithms can help implement the 6 th S in 5S+1 through monitoring and detecting workers who fail to adhere to standard safety practices such as wearing Personal Protective Equipment (PPE).The paper evaluated and analyzed three different detection approaches and compared their performance metrics. In total, seven models were proposed to perform such a task. All the proposed models utilized You-Only-Look-Once (YOLO v7) architecture to verify workers' PPE compliance. In approach I, three models were used to detect workers, safety helmets and safety vests. Then, a machine learning algorithm was used to verify if each detected worker is in PPE compliance. In approach II, the model simultaneously detects individual workers and veri es PPE compliance. In approach III, three different models were used to detect workers in the input feed. Then, a deep learning algorithm was used to verify the safety. All models were trained on Pictor-v3 dataset. It is found that the third approach, when utilizing VGG-16 algorithm, achieves the best performance, i.e., 80% F1 score, and can process 11.79 Frames per Second (FPS), making it suitable for real-time detection.

show abstract

Section: Vgg-16mentioning

confidence: 99%

Enhanced safety implementation in 5S + 1 via object detection algorithms

Shahin

Chen

Hosseinzadeh

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…In this paper, we apply the segmentation methods in Section 2.1 to these public datasets [19,20] to extract information of road objects for the prediction of QOL scores. The detail of the CamVid dataset is in Section 3.2.1.…”

Section: The Public Datasetsmentioning

confidence: 99%

“…Kantavat et al [18] proposed using deep convolutional neural networks (DCNNs), including semantic segmentation and object detection, to extract mobility factors in transportation from images. Thitisiriwech et al [19] presented a Bangkok Urbanscapse dataset, which is the first labeled streetscape dataset in Bangkok, Thailand, and also proposed efficient models for processing semantic segmentation.…”

Section: Introductionmentioning

confidence: 99%

Quality of Life Prediction in Driving Scenes on Thailand Roads Using Information Extraction from Deep Convolutional Neural Networks

et al. 2023

Self Cite

View full text Add to dashboard Cite

In the modern era, urban design and sustainable development are vital topics for megacities, as they are important for the wellbeing of its residents. One of the effective key performance indices (KPIs) measuring the city plan’s efficiency in quantity and quality factors is Quality of Life (QOL), an index that policymakers can use as a critical KPI to measure the quality of urbanscape design. In the traditional approach, the researchers conduct the questionnaire survey and then analyze the gathered data to acquire the QOL index. The conventional process is costly and time-consuming, but the result of the evaluation area is limited. Moreover, it is difficult to embed in an application or system; we proposed artificial intelligence (AI) approaches to solve the limitation of the traditional method in Bangkok as a case study. There are two steps for our proposed method. First, in the knowledge extraction step, we apply deep convolutional neural networks (DCNNs), including semantic segmentation and object detection, to extract helpful information images. Second, we use a linear regression model for inferring the QOL score. We conducted various state-of-the-art (SOTA) models and public datasets to evaluate the performance of our method. The experiment results show that our novel approach is practical and can be considered for use as an alternative QOL acquisition method. We also gain some understanding of drivers’ insights from the experiment result.

show abstract

“…This allows the network to capture spatial information and channel-wise interactions separately, making parameters more e cient and effective [101]. XceptionNet achieved stateof-the-art results on the ImageNet classi cation task and has since been used as a backbone architecture in many computer vision applications, such as object detection and semantic segmentation [102,103].…”

Section: Xceptionnetmentioning

confidence: 99%

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Shahin¹,

Chen

Hosseinzadeh³

et al. 2023

Preprint

View full text Add to dashboard Cite

The global steel demand continues to increase, with steel being used in various industries, including construction, automobile, national defense, and machinery. However, steel production is a delicate process that can result in different defects on the steel surface, negatively affecting the quality of the steel products. Therefore, recognizing metal surface defects is critical in the metal production industry. Manual detection of these defects is the standard method, but it is time-consuming, labor-intensive, and prone to subjective factors, leading to low accuracy and unreliable results. Automated defect detection using computer vision methods can replace or supplement manual detection. In recent years, machine learning algorithms, particularly Convolutional Neural Networks (CNNs), have shown great promise in achieving high accuracy rates in this task. In addition, image classification algorithms can contribute to Lean metal production by identifying defects or anomalies in the manufacturing process, which can be used to reduce waste and increase efficiency. However, the performance and cost of different CNN architectures can vary widely, making it challenging for decision-makers to select the most suitable model. This paper analyzes various CNN-based image classification algorithms, including MobileNet, ShuffleNet, DenseNet, RegNet, and NasNet, in classifying steel surface defects in the NEU-CLS-64 dataset. We evaluate their performance using metrics such as accuracy, precision, sensitivity, specificity, F1 score, and G-mean, and benchmark these models against each other. Our findings revealed that RegNet achieved the highest accuracy, precision, sensitivity, specificity, F1 score, and G-mean performance but at a higher cost than other models. Meanwhile, MobileNet had the lowest performance. The results provide decision-makers with valuable insights into selecting the most suitable CNN model for steel surface defect detection based on their performance.

show abstract

The Bangkok Urbanscapes Dataset for Semantic Urban Scene Understanding Using Enhanced Encoder-Decoder With Atrous Depthwise Separable A1 Convolutional Neural Networks

Cited by 10 publications

References 43 publications

Enhanced safety implementation in 5S + 1 via object detection algorithms

Enhanced safety implementation in 5S + 1 via object detection algorithms

Quality of Life Prediction in Driving Scenes on Thailand Roads Using Information Extraction from Deep Convolutional Neural Networks

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Contact Info

Product

Resources

About