Real-time Vehicle Detection implementing Deep Convolutional Neural Network features Data Augmentation Technique

Abstract

Background/Objectives: In this progressive Hi-Tech ecosystem, the cuttingedge technologies in the Deep Learning techniques for Vehicle Detection and Classification engendered swift paradigm shifts in diverse operations through the deployment of convolutional neural models in the Traffic Surveillance System. The fundamental element of the Traffic management system constitutes a real-time dynamic image, which forms the base input for vehicle recognition systems. The deep model functionalities on these base static images are highly pragmatic, and a radical approach leads to its successful applicability. Methods: This study proposes Faster Region-based Convolutional Neural Network (R-CNN) technique for image-based vehicle detection with significant performance benefits. Essentially, the base network of a pre-trained deep model, fine-tuned VGG-16 is transformed into Faster R-CNN. At this stage, the framework is constructed for a customized finitecapacity vehicle dataset. Subsequently, it is applied to train and test the system. From the performance lens, for further system enhancement, the speedup Bottleneck, and Data Augmentation implementation improve training speed and accuracy. Findings: The Experiments demonstrate that the sensitivity factor is 93.5% which provides acceptable results of 87.6% with 0.42s in vehicle detection in aspects of accuracy and execution time. Novelty : For our customized dataset, the performance-enhanced detection framework shows an increase of 4% in sensitivity and 3.23s with respect to time as compared to the other existing models. The proposed research is designed for a novel Faster RCNN algorithm that is fine-tuned detection algorithm of vehicles integrating sophisticated approaches for dynamic transformation of the live traffic video stream recording by transposing these real-time traffic videos to image inputs to this optimized detection framework achieving a high sensitivity factor with an efficient computation stack benefiting cost and time.https://www.indjst.org/

Deep Learning Approach for Volume Estimation in Earthmoving Operation

“…For a given video collected from various angles, scales, and illuminations, the model distinguished specific motions of the construction equipment. A vehicle classification approach using a pre-trained deep model such as VGG16 was implemented to pre-train the deep model with efficiency-oriented system settings and to increase the chance of using the model in minimumcapacity datasets by optimizing over-fitting limits [20].…”

Improved Spatial Invariance for Vehicle Platoon Application using New Pooling Method in Convolution Neural Network

“…Standard formulae of accuracy, precision, recall, and F1 score, as indicated ( 5) through (8), were used to evaluate the performance of three distinct pooling procedures. Here, True Positive (TP) is a correctly predicted class, False Positive (FP) is a label that does not belong to class but is predicted as positive, True Negative (TN) is the correctly predicted for class that does not belong to the class, False Negative (FN) is wrongly predicted for class that does not belong to the class.…”

“…Open repository datasets may not contain all of the images needed to do experimental work on the specified topic. In another instance, researchers have created datasets for vehicle rear parts in [8], and a few vehicle datasets are published in open source PKU-VD [9], VeRi-776 [10], VehicleID [11], as well as different vehicle datasets are available for smart city study [12]. But, to get dataset access from open source, researchers need to get approval from the owners.…”