Heading Direction Estimation Using Deep Learning with Automatic Large-scale Data Acquisition

Berriel, Rodrigo F.; Tabelini, Lucas; Cardoso, Vinicius B.; Guidolini, Rânik; Badué, Claudine; Souza, Alberto F. De; Oliveira-Santos, Thiago

doi:10.1109/ijcnn.2018.8489154

Cited by 11 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Faster R-CNN feature extractor was initialized with the ResNet-101 [35] weights, which was trained on the ImageNet dataset [36]. This pre-trained model was downloaded from the TensorFlow website 4 . Anchor scales and ratios were defined considering the application working range as [4,8,16,32] and [0.5, 1, 2], respectively.…”

Section: ) Cycleganmentioning

confidence: 99%

“…Deep learning techniques have enabled the emergence of several state-of-the-art models to address problems in different domains, such as image classification [1], [2], regression [3], [4], and object detection [5], [6], which is the focus of this work. However, these techniques are data-driven, which means that the performance achieved in a test dataset strongly depends on the training dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night

Arruda

Paixão

Berriel

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

102

View full text Add to dashboard Cite

Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy to the training dataset which must resemble the images in the target task. The acquisition of a dataset involves annotating images, an arduous and expensive process, generally requiring time and manual effort. Thus, a challenging scenario arises when the target domain of application has no annotated dataset available, making tasks in such situation to lean on a training dataset of a different domain. Sharing this issue, object detection is a vital task for autonomous vehicles where the large amount of driving scenarios yields several domains of application requiring annotated data for the training process. In this work, a method for training a car detection system with annotated data from a source domain (day images) without requiring the image annotations of the target domain (night images) is presented. For that, a model based on Generative Adversarial Networks (GANs) is explored to enable the generation of an artificial dataset with its respective annotations. The artificial dataset (fake dataset) is created translating images from day-time domain to night-time domain. The fake dataset, which comprises annotated images of only the target domain (night images), is then used to train the car detector model. Experimental results showed that the proposed method achieved significant and consistent improvements, including the increasing by more than 10% of the detection performance when compared to the training with only the available annotated data (i.e., day images).

show abstract

Section: ) Cycleganmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night

Arruda

Paixão

Berriel

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

102

View full text Add to dashboard Cite

show abstract

“…The success of deep learning applications on autonomous driving and advanced driver assistance systems (ADAS) is unequivocal. For instance, DNNs have been used in scene semantic segmentation [2], traffic light detection [3], crosswalk classification [4], [5], traffic sign detection [6], pedestrian analysis [7], car heading direction estimation [8] and many other applications. In this work, we focus on the traffic sign detection problem.…”

Section: Introductionmentioning

confidence: 99%

Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images

Tabelini

Paixão

Berriel

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Deep learning has been successfully applied to several problems related to autonomous driving. Often, these solutions rely on large networks that require databases of real image samples of the problem (i.e., real world) for proper training. The acquisition of such real-world data sets is not always possible in the autonomous driving context, and sometimes their annotation is not feasible (e.g., takes too long or is too expensive). Moreover, in many tasks, there is an intrinsic data imbalance that most learning-based methods struggle to cope with. It turns out that traffic sign detection is a problem in which these three issues are seen altogether. In this work, we propose a novel database generation method that requires only (i) arbitrary natural images, i.e., requires no real image from the domain of interest, and (ii) templates of the traffic signs, i.e., templates synthetically created to illustrate the appearance of the category of a traffic sign. The effortlessly generated training database is shown to be effective for the training of a deep detector (such as Faster R-CNN) on German traffic signs, achieving 95.66% of mAP on average. In addition, the proposed method is able to detect traffic signs with an average precision, recall and F1-score of about 94%, 91% and 93%, respectively. The experiments surprisingly show that detectors can be trained with simple data generation methods and without problem domain data for the background, which is in the opposite direction of the common sense for deep learning.

show abstract

“…[17]- [19]. Besides, DNNs are also a well-established approach in traffic flow prediction [20], [21], automatic driving fault prediction [22], and railway track circuit conflict detection [9], [23].…”

Section: Related Workmentioning

confidence: 99%

Towards Safety-Risk Prediction of CBTC Systems With Deep Learning and Formal Methods

et al. 2020

View full text Add to dashboard Cite

Communication-Based Train Control System (CBTC) system is an automated system for train control based on bidirectional train-ground communication. Safety-risk estimation is a vital approach that strives to guide the CBTC system to guarantee the safe operation of vehicles. We propose a deep learning method to predict safety-risk states that combined with formal methods. First, the impact factors are selected, and the movement authorization (MA) failure rate is calculated by statistical model checking. Then, we use a deep neural network to model the relationship between the safe-risk states and the train operation status. Experimental results show that our method can achieve an accuracy of 97.4% on safety-risk prediction, and exceeds the baseline methods. INDEX TERMS Communication-based train control system, risk prediction, deep learning, statistic model checking.

show abstract

Heading Direction Estimation Using Deep Learning with Automatic Large-scale Data Acquisition

Cited by 11 publications

References 24 publications

Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night

Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night

Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images

Towards Safety-Risk Prediction of CBTC Systems With Deep Learning and Formal Methods

Contact Info

Product

Resources

About