Vision-based real-time vehicle detection and vehicle speed measurement using morphology and binary logical operation

Nematzadeh

et al. 2022

Preprint

Morphological operators for binary and grayscale images are commonly used to eliminate noise, recognize contours or specific structures, and arrange shapes in image processing. Even though morphology has been substantially developed in square-pixel-based-image-processing (SIP), no effort has been made to construct morphological operators in hexagonal-pixel-based-image-processing (HIP) yet. In this paper, we transform basic SIP-domain-morphological operators such as dilation, erosion, closing, and opening into HIP-domain and compare their performance with their SIP counterparts, taking into account 65 similarity- dissimilarity metrics for binary and four metrics for grey-scale proposed so far in the literature. It is the first time to give the fundamental morphological operators in the HIP domain. The operators developed in this paper initiate the research about morphology in the HIP domain by successfully filling a significant gap by eliminating HIP's lack of basic operators.

Section: Properties Of the Dilation Operation Arementioning

confidence: 99%

Morphology for Hexagonal Image Processing

Nematzadeh

et al. 2022

Preprint

“…Another paper (9) introduces a real-time vehicle detection and Vehicle Speed Measurement (VSM) system using image processing techniques, specifically morphology operations and binary logical processes. The process begins with capturing an image from a video sensor and selecting Regions of Interest (ROI) through a dual-line approach where the two lines are separated by a measurable distance (10) .…”

Section: Introductionmentioning

confidence: 99%

Vehicle Speed Detection using Haar Cascade Classifier and Correlation Tracking

Siddiqua,

Saher,

Sumera

2024

IJST

Objectives: The aim of this study is to develop an efficient and cost-effective solution for predicting vehicle speeds using recorded video data. Methods: The proposed system employs a combination of image processing techniques and computer vision to calibrate cameras for traffic simulation, enabling the extraction of information on average vehicle speeds. It utilizes the Haar Cascade Classifier for object detection, followed by a correlation tracker for vehicle tracking. Speed estimation is achieved through the frame differencing method. The dataset comprises 90 minutes of recorded data from highway cameras, showcasing diverse traffic scenarios with various vehicle types (trucks, trailers, cars, buses, and bikes) at varying speeds. Predicted values are compared with ground truth data obtained from a GPS-equipped car, using Mean Absolute Error (MAE) as the evaluation metric. Findings: The algorithm's performance is evaluated, resulting in an average error rate of 1.72 km/h (2.07%). These findings are compared with state-of-the-art data. Novelty: This study introduces a novel system that combines the Haar Cascade Classifier, correlation tracker, and frame differencing method to track vehicle positions, incorporating bike detection into the analysis, and calculate their moving speeds. A relative analysis underscores the system's performance, emphasizing its effectiveness in real-world applications and demonstrating refinement in accuracy assessment. Keywords: Image processing, Vehicle speed estimation, Haar Cascade Classifier, Correlation tracker, Error rate calculation, Computer vision

“…Other branches of AI, e.g., machine learning, often interact with computer vision in various ways to improve performance and automation through a training loop (Azghadi et al, 2020; He et al, 2017; Katija et al, 2021; Khan et al, 2021). Designed to function similarly to human vision and to automate human tasks, this interdisciplinary field has had success in reading handwritten/printed text, identifying human faces, detecting human postures and movements, guiding autonomous vehicles, and measuring the dimensions of common objects in an anthropogenic context (e.g., Falcini et al, 2017; Hu et al, 2012; Lin et al, 2014; Permaloff & Grafton, 1992; Singh et al, 2022; Sonka et al, 2014; Trinh et al, 2012; Trivedi et al, 2022). However, the techniques and applications of computer vision, along with machine learning, are relatively underdeveloped in the field of marine mammal science (Dujon & Schofield, 2019; Gray et al, 2019; Li et al, 2022; Weinstein, 2018), and few studies have offered solutions to automate fine‐scale photogrammetry in cetaceans.…”

Section: Introductionmentioning

confidence: 99%

Computer vision‐assisted photogrammetry and one‐image 3D modeling in marine mammals

Zhang,

Zhou,

Shah

et al. 2023

Marine Mammal Science

Image processing using traditional photogrammetric methods is a labor‐intensive process. The collection of photogrammetry images during aerial surveys is expanding rapidly, creating new challenges to analyze images promptly and efficiently, while reducing human error during processing. Computer vision‐assisted photogrammetry, a field of artificial intelligence (AI), can automate image processing, greatly enhancing the efficiency of photogrammetry. Here, we present a practical and efficient program capable of automatically extracting the fine‐scale photogrammetry of East Asian finless porpoises (Neophocaena asiaeorientalis sunameri). Our results indicated that computer vision‐assisted photogrammetry could achieve the same accuracy as traditional photogrammetry, and the results of the comparisons were validated against the direct measurements. Three‐dimensional (3D) models using computer vision‐assisted photogrammetric morphometrics generated trustworthy body volume estimates. We also explored the one image‐based 3D modeling technique, which is less accurate, but still useful when only one image of the animal is available. Although several limitations exist in the current program, improvements could be made to narrow the virtual‐reality gap when more images are available for machine learning and training. We recommend this program for analyzing images of marine mammals possessing a similar morphological contour.