Automated Passenger Detection and Toll Processing System Using Convolution Neural Network
Rishabh Dara,
Alex Sumarsono
Issue:
Volume 8, Issue 1, June 2022
Pages:
1-5
Received:
5 March 2022
Accepted:
28 March 2022
Published:
9 April 2022
DOI:
10.11648/j.ajnna.20220801.11
Downloads:
Views:
Abstract: As a way to incentivize more people to drive multi-passenger vehicles, policies for high-occupancy vehicle (HOV) lanes and congestion toll discount are put in place at various locations. Being able to identify the correct number of people in a vehicle using the lanes is paramount in deciding the toll for that vehicle. In general, these lanes are operated based on voluntary declarations by the drivers, which makes it prone to abuse where vehicles with fewer occupants than required illegally use the HOV lanes. Hence, the capability to detect violators in real time is very critical. However, in many of the cases, vehicle occupancy detection relies on a labor-intensive manual method. This is quite unreliable and costly in terms of significant loss of revenue. This study proposes to remedy this problem by applying an object detection algorithm based on a deep convolutional neural network, known as the YOLO algorithm. This algorithm can automatically detect the number of occupants in a vehicle with very high degree of accuracy. Images are captured through Near Infrared (NIR) cameras on the HOV lanes. With proper fusion, clear signatures or silhouettes of the front passengers' faces are distinguishable from other inanimate objects in the vehicle. Using YOLOv3 the accuracy reaches 96%. This information is then used to charge the express lane toll. It is estimated that up to 95% of potential loss of revenue could be avoided. It is, therefore, a viable and attractive solution.
Abstract: As a way to incentivize more people to drive multi-passenger vehicles, policies for high-occupancy vehicle (HOV) lanes and congestion toll discount are put in place at various locations. Being able to identify the correct number of people in a vehicle using the lanes is paramount in deciding the toll for that vehicle. In general, these lanes are op...
Show More
Intelligent Based Image Processing Model for Ethiopian Enset Diseases Diagnosis
Issue:
Volume 8, Issue 1, June 2022
Pages:
6-11
Received:
24 November 2021
Accepted:
13 June 2022
Published:
21 June 2022
DOI:
10.11648/j.ajnna.20220801.12
Downloads:
Views:
Abstract: The downfall of agriculture is highly rampant in many developing countries such as Ethiopia, Pakistan, Bangladesh, Afghanistan, Eritrea, India and others. This is so a great focus in our country’s strategic plan for contributing growth of economy. There are many issues to decline this potential field, viz. weather, shortage of rain, pollution and diseases. However, Enset crops in Ethiopia are attacked by numerous insect pests and diseases which have been one of the difficulties in the development of agricultural sector. To handle these problems, experienced farmers and domain experts should only use visual inspection for the diagnosis of such plant diseases in-place. This has defects due to lowering the accuracy rate when compare to soft computing approaches. This research dealt with an intelligent based image processing techniques for Enset disease diagnosis to examine the various Enset leaf diseases. In order to create the knowledge base system, a total of 570 sample Enset images for the three diseases including Enset bacterial wilt, Enset black sigatok and Enset panama wilt are employed and this real dataset was demonstrated using MatLab R2020b platform. In the first stage, the image of the Enset disease is subjected to image processing techniques. Particularly, the possibility distribution algorithm applied to enhance the contrast of inputted image, followed the Otsu method used to select region of interest and then features such as GLCM, color and shape are extracted. Next a comparative analysis was made using various machine learning algorithms to identify each class labels based on the trained patterns. The developed system can successfully identify the examined Enset diseases using ANN and Kernel RBF with an accuracy of 91.8% and 79.41% respectively.
Abstract: The downfall of agriculture is highly rampant in many developing countries such as Ethiopia, Pakistan, Bangladesh, Afghanistan, Eritrea, India and others. This is so a great focus in our country’s strategic plan for contributing growth of economy. There are many issues to decline this potential field, viz. weather, shortage of rain, pollution and d...
Show More
