Multi-View Fine-Grained Vehicle Classification with Multi-Loss Learning

Assigning unique consecutive numerical identifiers (IDs) to the nodes of a multi-hop wireless network is an important problem, as it enables critical functions such as resource distribution (e.g., TDMA time slots) and leader election. If also used as a mean to “shorten” otherwise assigned node IDs node enumeration saves energy and imposes lower complexity. In this paper we present an efficient scheme for enumerating the N nodes of a multi-hop wireless network. Our protocol, called WiEnum for Wireless Enumeration, is distributed and, by means of the sole exchange of packets among neighbors, terminates with each node having a unique ID in the range 1 to N. Through Castalia-based simulations we demonstrate the effectiveness of WiEnum in assigning unique, short IDs by comparing its performance to that of another leading algorithm for ID assignments, termed SIDA. Our results show that, in terms of completion time (i.e., the time it takes till each node gets its unique ID) WiEnum outperforms SIDA, especially in networks with higher number of nodes and density. At the same time, WiEnum keeps energy consumption to levels that are always lower than those of SIDA.

ATC (Automatic toll collection) system that is used in the highway, bridge and tunnel. This paper discusses the concept of use of RFID (Radio Frequency Identification) in vehicle identification and auto debit of toll amount. The structural design of entire system that stores data on centralized server and facilitate efficient access for the purpose of toll collection in relatively predicted route is proposed. In case of nonpayment at toll center, the jamming concept is introduced that forces the vehicle to stop at the shortest possible distance from toll centre. The auto debit system which mainly relies upon minimum balance also takes care of over utilization of auto toll system when the balance goes below threshold. The privacy issues of RFID are discussed. The size and various types of RFID tags are discussed. Thus the system is proposed to make much more efficient than manual toll system and reduce traffic congestion at toll center.

The toll collection is becoming a major problem on the highways leading to large waiting queues. Toll gates installed on highways result in increased waiting time and fuel usage. In this paper, a study on automated toll collection system using radio frequency identification (RFID)-based system is presented, which provides fast identification of vehicles and toll collection. Using this system, the identification can be done just by slowing down the speed of the vehicle when it is passing from the toll plaza. The RFID reader scans the RFID tag or card and deducts the amount from it. The research analysed the system by proposing a mechanism and implementing an example scenario, which considered the random arrival of different vehicles. This technique is also compared with other existing mechanisms such as number plate recognition and barcode-based passes, which showed the need to utilise this technique for toll collection.

Convolutional neural network (CNN) has shown phenomenal results on several image classification applications. The performance of CNN is improved with deeper architectures. However, increasing depth comes with certain drawbacks like overfitting and need for more computational resources. Thus, it is necessary to choose optimal depth for a network. In this work, the empirical relation between model depth, capacity and complexity of data is estimated using proposed extended VGGNET (EVGGNET). The EVGGNET consists of feature extraction and classification network. The feature extraction network is divided into pre-trained and extended sections which extract the significant features. The classification network uses these features to classify input image into one of the categories. The basic idea behind EVGGNET is to extend the pre-trained feature extraction network by adding convolutional layers which help to establish the model capacity relationship. VGGNET is used as a pre-trained feature extraction network. The experiments are performed on benchmark datasets Caltech 101 and Caltech 256. The results show that the accuracy of EVGGNET is almost exponentially proportional to the complexity of data.

Convolutional Neural Networks (CNN) have achieved great performance in many visual tasks. However, CNN models are sensitive to samples with large spatial variants, especially severe in fine-grained classification task. In this paper, we propose a novel CNN model called ST-BCNN to solve these problems. ST-BCNN contains two functional CNN modules: Spatial Transform Network (STN) and Bilinear CNN(BCNN). Firstly, STN module is used to select key region in input samples and get it spatially modified. Since the adoption of STN will cause an information loss phenomenon called boundary loss, we design a brand-new IOU loss method to solve it. We make a theoretical analysis of the IOU loss method. Secondly, to discover discriminative features for fine-grained classification task, BCNN module is applied. BCNN interacts CNN features from different channels to produce more discriminative bilinear features than fully connected features of CNN. ST-BCNN works by reducing irrelevant spatial states and producing fine-grained features. We evaluate our model on 3 public fine-grained classification datasets with large spatial variants: CUB200-2011, Fish100 and UAV43. Experiments show that the IOU loss method can reduce boundary loss and make STN module output spatial transformed image appropriately. Our proposed ST-BCNN model outperforms other advanced CNN models on all three datasets.

Deep learning performs a great role in solving many problems, particularly with image classification. Still, the performance of many architectures is often limited at some points, especially with regular architecture. In this paper, we propose an efficient and noncomplex image classification architecture using deep learning based on the most popular algorithms: Convolutional Neural Network (CNN) for Feature extraction, Stacked AutoEncoder (SAE) for reducing the dimensionality, and Recurrent Neural Network (RNN) for increasing the accuracy. The proposed network, called Convolutional Stacked AutoEncoder Recurrent Neural Network (CSAERNet), that takes the input to be features-extracted by CNN then put as input to SAE for dimensionality reduction after that the RNN takes it as input to increase the accuracy. The proposed CSAERNet has been evaluated on two widely-used benchmark datasets; CIFAR-10 and CIFAR-100. The obtained results are compared with the latest state-of-the-art approaches, the results showed that the proposed CSAERNet perform well on both datasets and outperforms on other models.

A methodology for obtaining spatiotemporal information of the vehicles on bridges based on computer vision

Thus far, few studies have been conducted on fine-grained classification tasks for the latest convolutional neural network ConvNeXt, and no effective optimization method has been made available. To achieve more accurate fine-grained classification, this paper proposes two attention embedding methods based on ConvNeXt network and designs a new bilinear CBAM; simultaneously, a multiscale, multi-perspective and all-around attention framework is proposed, which is then applied in ConvNeXt. Experimental verification shows that the accuracy rate of the improved ConvNeXt for fine-grained image classification reaches 87.8%, 91.2%, and 93.2% on fine-grained classification datasets CUB-200-2011, Stanford Cars, and FGVC Aircraft, respectively, showing increases of 2.7%, 0.3% and 0.4%, respectively, compared to those of the original network without optimization, and increases of 3.7%, 8.0% and 2.0%, respectively, compared to those of the traditional BCNN. In addition, ablation experiments are set up to verify the effectiveness of the proposed attention framework.

Fine-grained image classification is one of the key basic tasks of computer vision. The appearance of traditional deep convolutional neural network (DCNN) combined with attention mechanism can focus on partial and local features of fine-grained images, but it still lacks the consideration of the embedding mode of different attention modules in the network, leading to the unsatisfactory result of classification model. To solve the above problems, three different attention mechanisms are introduced into the DCNN network (like ResNet, VGGNet, etc.), including SE, CBAM and ECA modules, so that DCNN could better focus on the key local features of salient regions in the image. At the same time, we adopt three different embedding modes of attention modules, including serial, residual and parallel modes, to further improve the performance of the classification model. The experimental results show that the three attention modules combined with three different embedding modes can improve the performance of DCNN network effectively. Moreover, compared with SE and ECA, CBAM has stronger feature extraction capability. Among them, the parallelly embedded CBAM can make the local information paid attention to by DCNN richer and more accurate, and bring the optimal effect for DCNN, which is 1.98% and 1.57% higher than that of original VGG16 and Resnet34 in CUB-200-2011 dataset, respectively. The visualization analysis also indicates that the attention modules can be easily embedded into DCNN networks, especially in the parallel mode, with stronger generality and universality.

Towards Fine-grained Recognition: Joint Learning for Object Detection and Fine-grained Classification

In traditional 3D reconstruction methods, using a single view to predict the 3D structure of an object is a very difficult task. This research mainly discusses human pose recognition and estimation based on 3D multiview basketball sports dataset. The convolutional neural network framework used in this research is VGG11, and the basketball dataset Image Net is used for pretraining. This research uses some modules of the VGG11 network. For different feature fusion methods, different modules of the VGG11 network are used as the feature extraction network. In order to be efficient in computing and processing, the multilayer perceptron in the network model is implemented by a one‐dimensional convolutional network. The input is a randomly sampled point set, and after a layer of perceptron, it outputs a feature set of n × 16. Then, the feature set is sent to two network branches, one is to continue to use the perceptron method to generate the feature set of n × 1024, and the other network is used to extract the local features of points. After the RGB basketball sports picture passes through the semantic segmentation network, a picture containing the target object is obtained, and the picture is input to the constructed feature fusion network model. After feature extraction is performed on the RGB image and the depth image, respectively, the RGB feature, the local feature of the point cloud, and the global feature are spliced and fused to form a feature vector of N × 1152. There are three branches for this vector network, which, respectively, predict the object position, rotation, and confidence. Among them, the feature dimensionality reduction is realized by one‐dimensional convolution, and the activation function is the ReLU function. After removing the feature mapping module, the accuracy of VC‐CNN_v1 dropped by 0.33% and the accuracy of VC‐CNN_v2 dropped by 0.55%. It can be seen from the research results that the addition of the feature mapping module improves the recognition effect of the network to a certain extent

Malignant liver tumors are considered as one of the most common cancers and a leading cause of cancer death worldwide. While using convolutional neural networks (CNNs) for feature extraction from ultrasound (US) images and tasks thereafter, most works focus on pre-trained architectures using transfer learning which can sometimes cause negative transfer and reduced performance in medical domain. A new method based on Pascal’s Triangle was developed for feature extraction using CNN. The convolutions and the kernels in Pascal’s Triangle based CNN (PT-CNN) are according to the coefficients at each level of Pascal’s Triangle. Due to the fuzzy nature of US images, the input layer takes a combination of the image and its neutrosophically pre-processed components as a single unit to improve noise robustness. The proposed CNN when implemented as a backbone for feature extraction for binary classification, gave validation accuracy > 90% and test accuracy >95% than other state-of-the-art CNN architectures. For tumor segmentation using Mask R-CNN framework, the aggregated feature maps from all convolutional layers were given as the input to the region proposal network for multiscale region proposals and to facilitate the detection of tumors of varying sizes. This gave an F1 score > 0.95 when compared with other architectures as backbone on Mask R-CNN framework and simple U-Net based segmentation. It is suggested that the promising results of PT-CNN as a feature extraction backbone could be further investigated in other domains.

Ensuring global food security requires accurate and robust solutions for crop health monitoring, weed detection, and large-scale land-cover classification. To this end, we propose AgroVisionNet, a hybrid deep learning framework that integrates Convolutional Neural Networks (CNNs) for local feature extraction, Vision Transformers (ViTs) for capturing long-range global dependencies, and Graph Neural Networks (GNNs) for modeling spatial relationships between image regions. The framework was evaluated on five diverse benchmark datasets—PlantVillage (leaf-level disease detection), Agriculture-Vision (field-scale anomaly segmentation), BigEarthNet (satellite-based land-cover classification), UAV Crop and Weed (weed segmentation), and EuroSAT (multi-class land-cover recognition). Across these datasets, AgroVisionNet consistently outperformed strong baselines including ResNet-50, EfficientNet-B0, ViT, and Mask R-CNN. For example, it achieved 97.8% accuracy and 95.6% IoU on PlantVillage, 94.5% accuracy on Agriculture-Vision, 92.3% accuracy on BigEarthNet, 91.5% accuracy on UAV Crop and Weed, and 96.4% accuracy on EuroSAT. These results demonstrate the framework’s robustness across tasks ranging from fine-grained disease detection to large-scale anomaly mapping. The proposed hybrid approach addresses persistent challenges in agricultural imaging, including class imbalance, image quality variability, and the need for multi-scale feature integration. By combining complementary architectural strengths, AgroVisionNet establishes a new benchmark for deep learning applications in precision agriculture.

An efficient utilization of communication link between RF Modems over a wireless channel to facilitate vehicle monitoring, vehicle authentication and automated toll collection on the highways is proposed. The system is implemented to automatically register vehicles getting on or off a motorway or highway, cutting the amount of time for paying toll in large queues. The detailed monthly bills will be sent to the customer at the end of the month. The customers could register and get a transmitter module and thereafter would not need to stop at toll booth whenever they get on or off the motorway. The implementation is divided into the design of two modules- the Vehicle Module (Active Tag) and the Base Module. The two modules communicate via RF modem connected to each module. These RF modules communicate over the ISM Frequency Range of 902 -- 928 MHz. The Vehicle module revolves around Atmel 8051 microcontroller. This module contains an LCD panel (16x2), keypad (4x3) and an RF modem interfaced to the microcontroller through Max-232 chip. Microcontroller contains user-specific data associated with vehicle, such as the Registration Number, Engine Number and owners information along with the billing address. The base module comes with a user-interface that allows the administrator to monitor the current activities in the range, including the vehicles in range, their status, and the detailed information about any registered vehicle. Moreover both, base and vehicle module can communicate with each other through chat session.

This paper presents an investigation study on facial emotional expression recognition. Three linear-decision-boundaries classifiers: linear support vector classification (LSVC), linear discriminant analysis (LDA) and softmax (SM) techniques are utilized based on convolutional neural network (CNN) for efficient feature extraction, namely CNN-LSVC, CNN-LDA and CNN-SM respectively. Hyper-parameter tuning or selection needs the least effort for such three linear-decision-boundaries classifiers. In order to enhance recognition performance, particular image preprocessing: intensity transformation as well as image cropping technique are implemented before feeding input images into CNN feature extraction. Relying on 10-fold cross validation of 80%-20% training-testing CK+ dataset, above 90% average results of precision, recall, F1 scores and accuracy rates are yielded by all such three investigated methods. Confusion matrix is also determined for more-detail of results examination.