Traffic Object Detection and Recognition Based on the Attentional Visual Field of Drivers

Shirpour, Mohsen; Khairdoost, Nima; Bauer, Michael; Beauchemin, Steven S.

doi:10.1109/tiv.2021.3133849

Cited by 19 publications

(4 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Imaging sensor and systems are widely used in machine vision-related fields such as industrial inspection, security monitoring, autonomous driving, etc [1][2][3][4][5] . Spectral responsivity is an important device parameter for system performance design and evaluation.…”

Section: Introductionmentioning

confidence: 99%

Investigation of spectral responsivity of imaging sensor and systems with a differential approach

Liu,

Gan,

Meng

et al. 2024

Sixth Conference on Frontiers in Optical Imaging and Technology: Novel Technologies in Optical Systems

View full text Add to dashboard Cite

Spectral responsivity is a key parameter for imaging sensors and systems. Traditionally, the spectral responsivity is measured in darkroom with no ambient light. However, the dark condition is not similar to most application science where ambient light generally exist. To investigate the ambient light bias effect on the detection performance, we introduce a differential approach to measure the spectral responsivity of the imaging sensors and systems under the biased lighting condition. The differential spectral responsivity (DSR) can reflect the target-environment interaction in complex scenes such as object detection in very bright/weak lighting environment or with very low image contrast. In this paper, a measurement facility for the differential spectral responsivity in irradiance mode in the waveband (300~1100)nm is established and described. The factors affecting the measurement are analyzed. As a case study, a standard relative uncertainty of 2.35% (k=1) is obtained for a CMOS sensor system in the waveband (400~800)nm.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation of spectral responsivity of imaging sensor and systems with a differential approach

Liu,

Gan,

Meng

et al. 2024

Sixth Conference on Frontiers in Optical Imaging and Technology: Novel Technologies in Optical Systems

View full text Add to dashboard Cite

show abstract

“…Visual object detection plays an important role in the field of computer vision. It has a variety of significant applications in human–computer interfaces, road traffic control, and video surveillance systems ( Ingle & Kim, 2022 ; Roy, 2017 ; Shirpour et al, 2023 ). In addition to classic applications, an increasing number of scholars are expanding the application of object detection to other fields, such as aquaculture and social computing ( Li et al, 2023 ; Wu et al, 2023 ).…”

Section: Introductionmentioning

confidence: 99%

Global vision object detection using an improved Gaussian Mixture model based on contour

Sun

2024

PeerJ Computer Science

View full text Add to dashboard Cite

Object detection plays an important role in the field of computer vision. The purpose of object detection is to identify the objects of interest in the image and determine their categories and positions. Object detection has many important applications in various fields. This article addresses the problems of unclear foreground contour in moving object detection and excessive noise points in the global vision, proposing an improved Gaussian mixture model for feature fusion. First, the RGB image was converted into the HSV space, and a mixed Gaussian background model was established. Next, the object area was obtained through background subtraction, residual interference in the foreground was removed using the median filtering method, and morphological processing was performed. Then, an improved Canny algorithm using an automatic threshold from the Otsu method was used to extract the overall object contour. Finally, feature fusion of edge contours and the foreground area was performed to obtain the final object contour. The experimental results show that this method improves the accuracy of the object contour and reduces noise in the object.

show abstract

“…Nevertheless, these methods exhibited limitations in terms of robustness and scalability. This was primarily attributed to their heavy dependence on manually crafted features and the need for extensive parameter adjustments [15,16]. Relying on the powerful feature extraction capabilities, deep learningbased object detection technologies could adaptively capture the deep semantic information of images through the multi-structured network models, thus significantly improving the efficiency and accuracy of detection tasks [17,18].…”

Section: Introductionmentioning

confidence: 99%

A Tiny Object Detection Approach for Maize Cleaning Operations

Yu,

Li,

et al. 2023

Foods

View full text Add to dashboard Cite

Real-time and accurate awareness of the grain situation proves beneficial for making targeted and dynamic adjustments to cleaning parameters and strategies, leading to efficient and effective removal of impurities with minimal losses. In this study, harvested maize was employed as the raw material, and a specialized object detection network focused on impurity-containing maize images was developed to determine the types and distribution of impurities during the cleaning operations. On the basis of the classic contribution Faster Region Convolutional Neural Network, EfficientNetB7 was introduced as the backbone of the feature learning network and a cross-stage feature integration mechanism was embedded to obtain the global features that contained multi-scale mappings. The spatial information and semantic descriptions of feature matrices from different hierarchies could be fused through continuous convolution and upsampling operations. At the same time, taking into account the geometric properties of the objects to be detected and combining the images’ resolution, the adaptive region proposal network (ARPN) was designed and utilized to generate candidate boxes with appropriate sizes for the detectors, which was beneficial to the capture and localization of tiny objects. The effectiveness of the proposed tiny object detection model and each improved component were validated through ablation experiments on the constructed RGB impurity-containing image datasets.

show abstract

Traffic Object Detection and Recognition Based on the Attentional Visual Field of Drivers

Cited by 19 publications

References 104 publications

Investigation of spectral responsivity of imaging sensor and systems with a differential approach

Investigation of spectral responsivity of imaging sensor and systems with a differential approach

Global vision object detection using an improved Gaussian Mixture model based on contour

A Tiny Object Detection Approach for Maize Cleaning Operations

Contact Info

Product

Resources

About