A Cascaded Part-Based System for Fine-Grained Vehicle Classification

Biglari, Mohsen; Soleimani, Ali; Hassanpour, Hamid

doi:10.1109/tits.2017.2749961

Cited by 48 publications

(20 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AlexNet [68] and VGG-16 [73]. The experimental results and conclusions are basically consistent with other studies on hierarchical models [8], [16], [55], [72], [74]. Parallelization and grading of neural networks is one of the developmental trends for deep learning.…”

Section: Discussionsupporting

confidence: 87%

“…Recently, a number of studies have been conducted on finegrained classification methods, and most of them provide promising performance in certain fields. Inspired by the design conceptions of parallel networks (e.g., Part-based CNN [8], Two-level Attention CNN [16], MCNN [55], GoogLeNet [72], ResNet [74], and Hypercolumn CNN [90]), we proposed a novel hybrid CNN structure codenamed M-bCNN, which leverages convolutional kernel matrixes to effectively increase the data streams, neurons, and link channels. The matrix-based architecture played an important role and the expected accuracy gains from it were delivered in the fine-grained image classification of wheat leaf diseases.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

et al. 2019

View full text Add to dashboard Cite

Fine-grained image classification methods often suffer from the challenge that the subordinate categories within an entry-level category can only be distinguished by subtle differences. Crop disease classification is affected by various visual interferences, including uneven illumination, dew, and equipment jitter. It demands an effective algorithm to accurately discriminate one category from the others. Thus, the representational ability of algorithm needs to be strengthened to learn a robust domain-specific discrimination through an effective way. To address this challenge, a unified convolutional neural network (CNN) denoting the matrix-based convolutional neural network (M-bCNN) was proposed. Its hallmark is the convolutional kernel matrix, whose convolutional layers are arranged parallelly in the form of a matrix, and integrated with DropConnect, exponential linear unit, local response normalization, and so on to defeat over-fitting and vanishing gradient. With a tolerable addition of parameters, it can effectively increase the data streams, neurons, and link channels of the model compared with the commonly used plain networks. Therefore, it will create more non-linear mappings and will enhance the representational ability with a tolerable growth of parameters. The images of winter wheat leaf diseases were utilized as experimental samples for their strong similarities among sub-categories. A total of 16 652 images containing eight categories were collected from Shandong Province, China, and were augmented into 83 260 images. The M-bCNN delivered significant improvements and achieved an average validation accuracy of 96.5% and a testing accuracy of 90.1%; this outperformed AlexNet and VGG-16. The M-bCNN demonstrated accuracy gains with a convolutional kernel matrix in fine-grained image classification. INDEX TERMS Convolutional neural network, fine-grained image classification, deep learning, convolutional kernel matrix, wheat leaf diseases.

show abstract

Section: Discussionsupporting

confidence: 87%

Section: Discussionmentioning

confidence: 99%

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In these methods the vehicle could be detected by passing through a fixed sensor, passing through the monitoring area, global coverage, or a hybrid of these methods [118][119][120]. Variety of information can be extracted using the sensors and detectors which may include vehicle count, shape-height, width and length- [121], speed [122], axle weight and spacing [123], acceleration/deceleration [124], make and model [125] and number plate [126].…”

Section: Vehicle-classification-based Methodsmentioning

confidence: 99%

Vehicle-Assisted Techniques for Health Monitoring of Bridges

Shokravi

Bakhary

et al. 2020

Sensors

View full text Add to dashboard Cite

Bridges are designed to withstand different types of loads, including dead, live, environmental, and occasional loads during their service period. Moving vehicles are the main source of the applied live load on bridges. The applied load to highway bridges depends on several traffic parameters such as weight of vehicles, axle load, configuration of axles, position of vehicles on the bridge, number of vehicles, direction, and vehicle’s speed. The estimation of traffic loadings on bridges are generally notional and, consequently, can be excessively conservative. Hence, accurate prediction of the in-service performance of a bridge structure is very desirable and great savings can be achieved through the accurate assessment of the applied traffic load in existing bridges. In this paper, a review is conducted on conventional vehicle-based health monitoring methods used for bridges. Vision-based, weigh in motion (WIM), bridge weigh in motion (BWIM), drive-by and vehicle bridge interaction (VBI)-based models are the methods that are generally used in the structural health monitoring (SHM) of bridges. The performance of vehicle-assisted methods is studied and suggestions for future work in this area are addressed, including alleviating the downsides of each approach to disentangle the complexities, and adopting intelligent and autonomous vehicle-assisted methods for health monitoring of bridges.

show abstract

“…Research on vehicles has always received great attention in many applications, such as vehicle detection [28]- [30], vehicle re-identification [31], [32], and fine-grained vehicle classification [33]- [35]. In this paper, we focus on vehicle detection based on unmanned aerial vehicle images.…”

Section: Related Work a Uav Vehicle Detectormentioning

confidence: 99%

Effective Contexts for UAV Vehicle Detection

2019

View full text Add to dashboard Cite

Vehicle detection based on unmanned aerial vehicle (UAV) images is a challenging task for the small size of objects, complex background, and the imbalance of various vehicle samples. This paper proposes a high-performance UAV vehicle detector. We use the single-shot refinement neural network (RefineDet) as a base network, which employs the top-down architecture to offer contextual information, achieving accurate detection. However, for the small size of vehicles, the top-down architecture introduces too much context, which brings surrounding interference. We present a multi-scale adjacent connection module (ACM) to provide effective contextual information and reduce interference for vehicle detection. In addition, we adopt an alternate double loss training strategy (ADT) to solve the problem of imbalance between hard and easy examples during training, and we design suitable default boxes according to the distribution of the UAV dataset to improve the recall rate. Our method achieves 92.0% and 90.4% accuracy on the collected UAV dataset and the publicly available Stanford drone dataset, respectively. And, the proposed detector can run at 58 FPS on a single GPU. INDEX TERMS Adjacent connection module, effective contexts, alternate double loss, unmanned aerial vehicle, detection.

show abstract

A Cascaded Part-Based System for Fine-Grained Vehicle Classification

Cited by 48 publications

References 31 publications

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

Vehicle-Assisted Techniques for Health Monitoring of Bridges

Effective Contexts for UAV Vehicle Detection

Contact Info

Product

Resources

About