Vehicle Brands and Types Detection Using Mask R-CNN

Nafi'i, Mohammad Wahyudi; Yuniarno, Eko Mulyanto; Affandi, Achmad

doi:10.1109/isitia.2019.8937278

Cited by 10 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When it comes to small numbers of labeled samples, the technique can help reduce the test/validation set error by imposing a regularizing effect. Many studies have illustrated the effectiveness of transferring learning in decreasing the overfitting effect while increasing the prediction accuracy of the Mask R-CNN algorithm in various fields like transportation ( 44,74–76 ), agriculture ( 77 ), and medical ( 78 , 79 ). Therefore, the research also applied this technique on the Rotated Mask R-CNN variants.…”

Section: Methodsmentioning

confidence: 99%

“…Parallel to the continued advancement of CV, applications of CV in transportation have been consistently expanding as well. CV applications in transportation engineering include the determination of distance measurements along roadways (38), the understanding of the vehicle environment in autonomous vehicles (39)(40)(41), vehicle identification and classification (42)(43)(44)(45), incident detection (46,47), pedestrian detection (48)(49)(50), as well as the detection of lane changes (51). Among the large selection of CV applications in transportation engineering, a considerable subset focuses on parking space management.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Rotated Mask Region-Based Convolutional Neural Network Detection for Parking Space Management System

Truong

Clay

Mora

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Parking space management systems help organize and optimize available parking spaces for consumers, making the process of finding and using parking spaces more efficient. Current parking space management systems include manual recognition, the employment of magnetic and ultrasonic sensors, and, recently, computer vision (CV). One relatively new region-based convolutional neural network (R-CNN) model, Mask R-CNN, has shown promise in its ability to detect objects and has demonstrated superior performance over many other popular CV methods. Building on Mask R-CNN, an updated version, Rotated Mask R-CNN, which can generate bounding boxes the axes of which are rotated with respect to the image’s axis, was proposed to address the limitation of Mask R-CNN. Albeit with the documented theoretical benefits, the application of the rotated version is rare because of its recent invention. To this end, the study aims to detect vehicle instances in one parking lot using various Rotated Mask R-CNN models based on unmanned aircraft system collected images. Both average precision and average recall were utilized to assess the performance of the alternative models with different backbone and head networks. The results reveal the high accuracy level associated with Rotated Mask R-CNN in real-time detection of vehicles. In addition, the results indicate that the inference speed and total loss are highly correlated with head networks and training schedules.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Rotated Mask Region-Based Convolutional Neural Network Detection for Parking Space Management System

Truong

Clay

Mora

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…On the other hand, neural network-based methods also grow vigorously. Many people changed their CNN according to famous networks, such as YOLO, YOLOv2, 19 YOLOv3, YOLOv4, 20 RCNN, 21 and faster-RCNN. Additionally, Soon et al 22 presented a vehicle logo detection method using a deep learning method and whitening transformation technique to remove the redundancy of adjacent image pixels.…”

Section: Vehicle Logo Detectionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Expressway vehicle logo detection: a lightweight CNN and logo localization method

Yue,

Fu,

Yang

2024

J. Electron. Imag.

View full text Add to dashboard Cite

Information about vehicles plays an important role in intelligent transportation systems (ITSs). It can be applied in different areas such as vehicle monitoring, vehicle detection, auxiliary reconnaissance, etc. Among the different types of vehicle-related information, logo information plays an essential role in quickly identifying the vehicle and enabling relevant work to be carried out. However, existing logo detection methods face issues related to low training accuracy and difficulty in accurately locating the logo, which leads to inaccurate detection of vehicle logos. To address these challenges, we first propose a method for detecting vehicle logos, particularly at expressway exits. We created a dataset comprising seven categories of vehicles for this purpose. Our solution includes a lightweight model that bridges CNN and transformer and a creative method for locating the logo. Additionally, we also do data processing on the test images to make them robust to environmental changes. The network that we designed is simple yet effective, achieving improvements in both precision and speed. Furthermore, our vehicle logo localization algorithm can withstand environmental variations. Experimental results demonstrate that our algorithm achieves a 5% to 10% accuracy boost compared with other methods.

show abstract

“…Figure 7 depicts the training and validation loss plotted against training epochs.The loss function here basically consists of classification loss (Loss cls ), bounding box loss (Loss bbox ) and mask loss (Loss mask )[38] Loss = Loss cls + Loss bbox + Loss mask(1) …”

mentioning

confidence: 99%

Detection of electrode misalignment and its effect on joint quality in resistance spot welding: a low-cost computer vision-based approach

Bhavsar,

Dutta,

Pal

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Electrode misalignment in resistance spot welding can be caused by poor fitting or deformation of electrode with continuous usage. This leads to asymmetric weld nugget formation, porosity and expulsion. This paper presents a novel low-cost real-time inspection system for angular misalignment using an image processing approach. The proposed solution can effectively segment the electrode tips even from the image captured at noisy industrial background such as automotive assembly line, by using a regional convolutional neural network based object identification method. The trained model has a mean average precision and recall of 99.01% and 96.6%, respectively. A series of image processing tools and mathematical operations were used to identify the edge line contours of electrode tips accurately from the detection mask, and determine the angular misalignment with a maximum deviation of less than 0.06˚. Experimental results showed that the weld nuggets exhibited porosity, shrinkage voids, and cracks when performed under angular misalignment conditions.

show abstract

Vehicle Brands and Types Detection Using Mask R-CNN

Cited by 10 publications

References 19 publications

Rotated Mask Region-Based Convolutional Neural Network Detection for Parking Space Management System

Rotated Mask Region-Based Convolutional Neural Network Detection for Parking Space Management System

Expressway vehicle logo detection: a lightweight CNN and logo localization method

Detection of electrode misalignment and its effect on joint quality in resistance spot welding: a low-cost computer vision-based approach

Contact Info

Product

Resources

About