Vehicle Detection and Categorisation Using Deep Learning Algorithms

Deep learning techniques help computer vision automatically learn the intrinsic patterns within complex data. This research mainly concentrates on creating a mobile application based on augmented reality for elderly mobile users that helps in identifying the traffic signals and other signboards in real‐time using deep learning techniques. TensorFlow serves as an implementation platform to build the object detection system with deep learning. The single shot multibox detector (SSD) model and the two‐stage faster‐regional convolutional neural network (RCNN) models from TensorFlow's object detection application programming interface (API) are compared in this study. The SSD model with MobileNet as a backbone network serves well for this study as it is faster than the RCNN model with comparable accuracy. However, unconstrained environments like occlusions can be an obstacle to the effective performance of an object detection system. This research provides a solution to handle occlusions by developing a robust object detection system through image segmentation techniques. The model introduced is based on the SSD MobileNet model which enables it to be deployable on mobile devices for real‐time offline detection. The developed model exhibits faster performance than the state‐of‐the‐art instance segmentation model, Mask RCNN with comparable accuracy. Elaborated implementation of this system and results are presented in further sections.

Conservation tillage, a crucial method for protecting soil fertility, depends heavily on maintaining adequate straw coverage. The current method of straw coverage detection relies primarily on manual measurement, which is both time-consuming and laborious. This paper introduces a novel straw coverage detection approach based on an improved mask regional convolutional neural network (Mask R-CNN) algorithm. Several images of wheat straw-covered fields were taken, and the dataset was augmented using techniques like image inversion, contrast enhancement, Gaussian noise addition, and translation after cropping the original images. These fields use a crop rotation cycle of wheat and corn. Subsequently, the straw images were annotated using the Labelme annotation tool to obtain the available straw instance segmentation dataset. The Mask R-CNN algorithm was improved by refining the mask generation network structure through a multi-feature fusion strategy, which interweaves features from both the encoder and the mask generation network, enhancing the model’s ability to capture detailed and shape information of the straw. Lastly, using the mask information output by the improved Mask R-CNN algorithm, the straw coverage was calculated by counting the proportion of pixels within each segmented region. In the results, compared to the original Mask R-CNN algorithm, our improved Mask R-CNN algorithm achieved an average improvement of 7.8% in segmentation accuracy, indicating that the improved Mask R-CNN algorithm offers superior segmentation performance. Thus, the new algorithm can achieve straw coverage detection with higher accuracy and can provide a reference for other agricultural applications.

Designing of VehiNet Using Convolutional Neural Networks and Deep Learning Techniques

Accurate identification of vehicles and estimating density in traffic surveillance systems is a challenging task, particularly in scenarios with closely spaced lanes. Single Shot MultiBox Detector (SSD) is introduced in vehicle detection and classification due to its speed and accuracy. It utilizes a transfer learning technique that enables them to utilize features from pretrained Convolutional Neural Networks (CNNs). Although the utilization of multi-scale feature maps in SSD has achieved efficient results in vehicle detection, it struggles to identify key features of vehicles due to its one-stage detection approach. Furthermore, the use of VGG16 as the backbone network in these approaches leads to the loss of fine-grained details, posing challenges in accurately localizing and classifying small vehicles. Also, there is no interaction between high- and low-level features, which restricts the networks ability to effectively integrate and utilize both features for accurate vehicle detection. To overcome these limitations, an improved SSD approach is introduced in this paper, leveraging interactive multi-scale attention characteristics to accurately detect and classify vehicles. This approach utilizes ResNet50 as the network backbone to overcome the limitations of traditional SSDs in detecting small vehicles. Also, an attention block is incorporated into it to focus on key details and assign higher attention to relevant pixels within the feature map. Also, the network employs a parallel detection framework and shares multi-scale layers (both high and low), enabling efficient detection of vehicles with various sizes. Then, traffic density is estimated based on the weights assigned to the categorized vehicles obtained from the improved SSD and the recorded area. Finally, traffic is classified as high, low, or moderate by comparing the estimated density to a threshold value. By adding attention characteristics of different scales to the original detection branch and replacing the VGG16 with ResNet50 of the SSD technique using our method, the feature representation capability and detection accuracy are both significantly improved.

Purpose In order to resolve the situation of high missed diagnosis rate and high misdiagnosis rate of the pathological analysis of the gastrointestinal endoscopic images by experts, we propose an automatic polyp detection algorithm based on Single Shot Multibox Detector (SSD). Method In the paper, SSD is based on VGG-16, the fully connected layer is changed to a convolutional layer, and four convolutional layers with successively decreasing scales are added as a new network structure. In order to verify the practicability, it is not only compared with manual polyp detection but also with Mask R-CNN. Results Multiple experimental results show that the mean Average Precision (mAP) of the SSD network is 95.74%, which is 12.4% higher than the manual detection and 5.7% higher than the Mask R-CNN. When detecting a single frame of image, the detection speed of SSD is 8.41 times that of manual detection. Conclusion Based on the traditional pattern recognition algorithm and the target detection algorithm using deep learning, we select a variety of algorithms to identify and classify polyps to achieve efficient detection results. Our research demonstrates that deep learning has a lot of room for development in the field of gastrointestinal image recognition.

The use of computer vision and deep learning in boundary documentation for land registration stems from the ongoing demand for appropriate mapping approaches of unregistered land rights to eradicate the global challenge of tenure insecurity. Previous research has yielded promising results towards automated extraction of photo‐visible cadastral boundaries from high‐resolution imagery. Nonetheless, the extraction of invisible cadastral boundaries is still a challenge. This study investigates the place of sensor/s on‐board unmanned aerial vehicles and deep learning algorithms in detecting cadastral boundaries. It develops a participatory boundary marking procedure using low‐cost markers to bring monument to previously invisible and ill‐defined cadastral boundaries. After that, the researchers trained and tested the accuracy of a convolutional neural network, namely single shot multi‐box detector (SSD) based on Residual Neural Network (ResNet) and Visual Geometry Group (VGG) backbone networks to automatically detect cadastral boundary markers from unmanned aerial vehicle imagery. SSD based on ResNet34 performed best with 0.88 precision, 0.92 recall and 0.91 F measure or (F1) score. VGG19‐based SSD yielded a precision of 0.47, recall of 0.53 and F1 score of 0.50. The horizontal accuracy of the cadastral map generated varied from 0.089 to 0.496 m per parcel, with a standard deviation of 0.120 m. Results show that this approach is practical for cadastral mapping in rural areas.

Urban villages emerge with the rapid urbanization process in many developing countries, and bring serious social and economic challenges to urban authorities, such as overcrowding and low living standards. A comprehensive understanding of the locations and regional boundaries of urban villages in a city is crucial for urban planning and management, especially when urban authorities need to renovate these regions. Traditional methods greatly rely on surveys and investigations of city planners, which consumes substantial time and human labor. In this work, we propose a low-cost and automatic framework to accurately identify urban villages from high-resolution remote sensing satellite imagery. Specifically, we leverage the Mask Regional Convolutional Neural Network (Mask-RCNN) model for end-to-end urban village detection and segmentation. We evaluate our framework on the city-wide satellite imagery of Xiamen, China. Results show that our framework successfully detects 87.18% of the urban villages in the city, and accurately segments their regional boundaries with an IoU of 74.48%.

This study developed the reliable Mask R-CNN model to detect stomata in Lonicera caerulea. The obtained data could be utilized for evaluating some characters such as stomatal number and aperture area. The native distribution of haskap (Lonicera caerulea L.), a small-shrub species, extends through Northern Eurasia, Japan, and North America. Stomatal observation is important for plant research to evaluate the physiological status and to investigate the effect of ploidy levels on phenotypes. However, manual annotation of stomata using microscope software or ImageJ is time consuming. Therefore, an efficient method to phenotype stomata is needed. In this study, we used the Mask Regional Convolutional Neural Network (Mask R-CNN), a deep learning model, to analyze the stomata of haskap efficiently and accurately. We analyzed haskap plants (dwarf and giant phenotypes) with the same ploidy but different phenotypes, including leaf area, stomatal aperture area, stomatal density, and total number of stomata. The R-square value of the estimated stomatal aperture area was 0.92 and 0.93 for the dwarf and giant plants, respectively. The R-square value of the estimated stomatal number was 0.99 and 0.98 for the two phenotypes. The results showed that the measurements obtained using the models were as accurate as the manual measurements. Statistical analysis revealed that the stomatal density of the dwarf plants was higher than that of the giant plants, but the maximum stomatal aperture area, average stomatal aperture area, total number of stomata, and average leaf area were lower than those of the giant plants. A high-precision, rapid, and large-scale detection method was developed by training the Mask R-CNN model. This model can help save time and increase the volume of data.

Proper mask usage in public areas has been shown to be critical in the efforts to reduce infection spread in circumstances such as the COVID-19 pandemic. In this paper, we propose mask usage detection approach based on deep learning: a Mask Regional-Convolutional Neural Network (Mask R-CNN) that provides segmentation of faces and masks, and another CNN using a novel Soft Attention unit to detect the correctness of the mask usage. We also provide a small instance segmented subset of the Masked Faces (MAFA) dataset for instance segmentation problems. We use the Mask R-CNN to provide instance segmentations of faces and face masks to the visual relationship detection CNN and predict improperly and properly worn face masks. Various CNN architectures such as ResNet50 were tested and compared to determine its effectiveness for the above task. We evaluate the CNN architectures on accuracy, precision, recall, and specificity of detecting properly worn masks. The best performing network was determined to be the ResNet50V2 architecture with 76.27% accuracy, 84.76% precision, 74.38% recall, and 79.20% specificity.

Deep learning integral imaging for three-dimensional visualization, object detection, and segmentation

The aim of this study is to develop a predictive model utilizing deep learning and machine learning techniques that will inform clinical decision-making by predicting the 1-year postoperative recovery of patients with lumbar disk herniation. The clinical data of 470 inpatients who underwent tubular microdiscectomy (TMD) between January 2018 and January 2021 were retrospectively analyzed as variables. The dataset was randomly divided into a training set (n = 329) and a test set (n = 141) using a 10-fold cross-validation technique. Various deep learning and machine learning algorithms including Random Forests, Extreme Gradient Boosting, Support Vector Machines, Extra Trees, K-Nearest Neighbors, Logistic Regression, Light Gradient Boosting Machine, and MLP (Artificial Neural Networks) were employed to develop predictive models for the recovery of patients with lumbar disk herniation 1 year after surgery. The cure rate score of lumbar JOA score 1 year after TMD was used as an outcome indicator. The primary evaluation metric was the area under the receiver operating characteristic curve (AUC), with additional measures including decision curve analysis (DCA), accuracy, sensitivity, specificity, and others. The heat map of the correlation matrix revealed low inter-feature correlation. The predictive model employing both machine learning and deep learning algorithms was constructed using 15 variables after feature engineering. Among the eight algorithms utilized, the MLP algorithm demonstrated the best performance. Our study findings demonstrate that the MLP algorithm provides superior predictive performance for the recovery of patients with lumbar disk herniation 1 year after surgery.

Recent technological advancements allow deep learning to be employed in practically every aspect of life. Because deep learning techniques are so precise, they can be used in medicine to classify and detect various diseases. The coronavirus (SARSCoV2) epidemic has recently affected global health systems. One of the ways to diagnose SARSCoV2 is with a chest X-ray. This paper proposes a deep learning technique to distinguish SARSCoV2 positive and normal cases. In this study, we fine-tuned the deep learning models and hyperparameters, and the fine-tuned deep learning models performed significantly better. To classify X-ray images, we developed a system based on deep learning algorithms that includes five models: Xception, VGG19, ResNet50, DenseNet121, and Inception. We offer deep learning models and algorithms that have been trained and evaluated to support medical efforts and reduce medical staff workload when dealing with SARSCoV2. In addition, the classification model that was proposed yields positive results because it makes use of accurate classification of the SARSCoV2 disease based on medical images. Additionally, the performance of our proposed CNN classification method for medical imaging was evaluated using various edge-based neural networks. The accuracy of tertiary classification with CNN will decrease as the number of classes in the training network grows. In tertiary classification, which includes normal and SARSCoV2 positive images, the proposed model achieved a 0.9897 accuracy. The proposed algorithm achieves a high level of classification accuracy when using the DenseNet121 model for binary classification.

Coronary artery disorder is the heart disease that is prevalent across the globe today. It's a serious issue for the humans as it requires proper diagnosis. Coronary artery disease develops over time as a result of plaque build- up in coronary arteries results in partial blockage of blood flow as the, which is primarily composed of cholesterol, calcium, and fibrin. Coronary arteries help human heart to pump oxygen-rich blood throughout the body by supplying it. However, appropriate diagnosis and early prediction will lessen the likelihood of developing it. This study explores the possibility of foreseeing cardiac illness at an early stage using deep learning algorithms. This study's primary goal is to properly determine whether a person has heart problems or not. by using deep learning techniques, Deep learning and various machine learning algorithms can both be used to implement early-stage prediction. Data mining, Decision trees, Naive Bayes, Artificial Neural Networks (ANN) are some examples through which it can be implemented. The research is going to be done using ANN Model.

A systematic literature review on machine learning and deep learning-based covid-19 detection frameworks using X-ray Images

One of the key tasks for a robot operating in uneven terrain, such as in disaster areas, is the search and retrieval of a target object. It is advantageous for the robot to perform these tasks autonomously. With the aim of achieving autonomous object search and retrieval for a tracked mobile robot, this study investigates an object search motion that incorporates object detection and retrieval for a spray can, which serves as the target object, using a quadruped tracked mobile robot developed by the authors. In the object search, the robot utilizes a vision camera to detect the target object. A deep learning model, the Single Shot Multibox Detector (SSD), is employed for object detection, as it is one of the widely used algorithms in deep learning for object localization. Additionally, an image cropping method and a tiling-based approach are applied to effectively detect objects located at longer distances. After the initial search for the object, the robot continuously detects the object through image extraction during its movement toward the target object. For the object retrieval motion, the position and orientation of the object are determined using the robot’s depth camera, based on edge detection. This information allows the robot to calculate the optimal grasping positions for both hands, which are mounted at the end of the front legs. The robot then repositions itself accordingly, aligns its hands with the calculated grasping positions, and executes the grasping motion to securely lift the object, using the front legs as manipulators. Using these methods, we conducted experiments with the robot to evaluate object search and retrieval in outdoor environments. The results demonstrated the robot’s ability to detect the target object at a long distance, move toward the object while maintaining detection, approach it, identify the optimal grasping position, and lift it. Experimental results confirmed the successful execution of these sequential motions for object search and retrieval.