Resource-Efficient Hardware Implementation of Perspective Transformation Based on Central Projection

Li, Zeying; Wang, Weijiang; Xue, Chengbo; Jiang, Rongkun

doi:10.3390/electronics11091367

Cited by 2 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when a robot is used to collect images, the camera plane is often not parallel to the pointer meter panel, so the collected pointer meter image may be in an ellipse. In this case, the pointer meter images to be inspected are distorted images [22]. Perspective transformation is to project an image onto a new visual plane to transform an ellipse into a circle.…”

Section: Image Perspective Transformationmentioning

confidence: 99%

“…perpendicular to the pointer meter dial, the captured pointer meter image is a circl ever, when a robot is used to collect images, the camera plane is often not paralle pointer meter panel, so the collected pointer meter image may be in an ellipse. In th the pointer meter images to be inspected are distorted images [22]. Perspective tr mation is to project an image onto a new visual plane to transform an ellipse into The circle is obtained using the condition that the perspective center, image po target point are collinear.…”

Section: Image Perspective Transformationmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Reflection Detection and Control Strategy of Pointer Meters Based on YOLOv5s

Liu

Deng

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Reflective phenomena often occur in the detecting process of pointer meters by inspection robots in complex environments, which can cause the failure of pointer meter readings. In this paper, an improved k-means clustering method for adaptive detection of pointer meter reflective areas and a robot pose control strategy to remove reflective areas are proposed based on deep learning. It mainly includes three steps: (1) YOLOv5s (You Only Look Once v5-small) deep learning network is used for real-time detection of pointer meters. The detected reflective pointer meters are preprocessed by using a perspective transformation. Then, the detection results and deep learning algorithm are combined with the perspective transformation. (2) Based on YUV (luminance-bandwidth-chrominance) color spatial information of collected pointer meter images, the fitting curve of the brightness component histogram and its peak and valley information is obtained. Then, the k-means algorithm is improved based on this information to adaptively determine its optimal clustering number and its initial clustering center. In addition, the reflection detection of pointer meter images is carried out based on the improved k-means clustering algorithm. (3) The robot pose control strategy, including its moving direction and distance, can be determined to eliminate the reflective areas. Finally, an inspection robot detection platform is built for experimental study on the performance of the proposed detection method. Experimental results show that the proposed method not only has good detection accuracy that achieves 0.809 but also has the shortest detection time, which is only 0.6392 s compared with other methods available in the literature. The main contribution of this paper is to provide a theoretical and technical reference to avoid circumferential reflection for inspection robots. It can adaptively and accurately detect reflective areas of pointer meters and can quickly remove them by controlling the movement of inspection robots. The proposed detection method has the potential application to realize real-time reflection detection and recognition of pointer meters for inspection robots in complex environments.

show abstract

Section: Image Perspective Transformationmentioning

confidence: 99%

Section: Image Perspective Transformationmentioning

confidence: 99%

Adaptive Reflection Detection and Control Strategy of Pointer Meters Based on YOLOv5s

Liu

Deng

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…PERSPECTIVE CORRECTION Perspective correction is an important image-processing task in computer vision. This operation can adjust distortion created by shooting from different angles and distances [12]. Perspective correction is image transformation from one plane view to another plane view which is desired by the application.…”

Section: Camera Calibrationmentioning

confidence: 99%

The Design of Vehicle Surround View Monitor

Juskova,

Kovac

2023

Proceedings of the 26th IMEKO TC4 International Symposium and 24th International Workshop on ADC/DAC Modelling and Testing

View full text Add to dashboard Cite

In this paper, the technology and design of a driving assistant called the Surround View Monitor (SVM) are discussed. The procedures used to create a unified, bird's-eye view are presented, which involve stitching images captured by strategically placed cameras on the vehicle. The proposed algorithm was successfully implemented on a car model and involves various stages, including camera calibration, photometric and perspective correction, scale planar transformation, and final image stitching. The paper should be considered student work and it is positioned as the foundation for the authors' future scientific work in the field of automated parking systems.

show abstract

Resource-Efficient Hardware Implementation of Perspective Transformation Based on Central Projection

Cited by 2 publications

References 29 publications

Adaptive Reflection Detection and Control Strategy of Pointer Meters Based on YOLOv5s

Adaptive Reflection Detection and Control Strategy of Pointer Meters Based on YOLOv5s

The Design of Vehicle Surround View Monitor

Contact Info

Product

Resources

About