Abstract

Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos. Document type: Part of book or chapter of book

Abstract

The use of Computer Vision techniques for the automatic recognition of road signs is fundamental for the development of intelligent vehicles and advanced driver assistance systems. In this paper, we describe a procedure based on color segmentation, Histogram of Oriented Gradients (HOG), and Convolutional Neural Networks (CNN) for detecting and classifying road signs. Detection is speeded up by a preprocessing step to reduce the search space, while classification is carried out by using a Deep Learning technique. A quantitative evaluation of the proposed approach has been conducted on the well-known German Traffic Sign data set and on the novel Data set of Italian Traffic Signs (DITS), which is publicly available and contains challenging sequences captured in adverse weather conditions and in an urban scenario at night-time. Experimental results demonstrate the effectiveness of the proposed approach in terms of both classification accuracy and computational speed. Document type: Part of book or chapter of book

Abstract

Vision based active safety systems have become more frequently occurring in modern vehicles to estimate depth of the objects ahead and for autonomous driving (AD) and advanced driver-assistance systems (ADAS). In this thesis a lightweight deep convolutional neural network performing real-time depth estimation on single monocular images is implemented and evaluated. Many of the vision based automatic brake systems in modern vehicles only detect pre-trained object types such as pedestrians and vehicles. These systems fail to detect general objects such as road debris and roadside obstacles. In stereo vision systems the problem is resolved by calculating a disparity image from the stereo image pair to extract depth information. The distance to an object can also be determined using radar and LiDAR systems. By using this depth information the system performs necessary actions to avoid collisions with objects that are determined to be too close. However, these systems are also more expensive than a regular mono camera system and are therefore not very common in the average consumer car. By implementing robust depth estimation in mono vision systems the benefits from active safety systems could be utilized by a larger segment of the vehicle fleet. This could drastically reduce human error related traffic accidents and possibly save many lives. The network architecture evaluated in this thesis is more lightweight than other CNN architectures previously used for monocular depth estimation. The proposed architecture is therefore preferable to use on computationally lightweight systems. The network solves a supervised regression problem during the training procedure in order to produce a pixel-wise depth estimation map. The network was trained using a sparse ground truth image with spatially incoherent and discontinuous data and output a dense spatially coherent and continuous depth map prediction. The spatially incoherent ground truth posed a problem of discontinuity that was addressed by a masked loss function with regularization. The network was able to predict a dense depth estimation on the KITTI dataset with close to state-of-the-art performance. 

Abstract

Pipelines are structural elements of many systems. For example, they are used in water supply and heat supply systems, in chemical production facilities, aircraft manufacturing, and in the oil and gas industry. Accidents in piping systems result in significant economic damage. An important factor for ensuring the reliability of energy transportation systems is the assessment of real technical conditions of pipelines. Methods for assessing the state of pipeline systems by their vibro-acoustic parameters are widely used today. Traditionally, the Fourier transform is used to process vibration signals. However, as a rule, the oscillations of the pipe-liquid system are non-linear and non-stationary. This reduces the reliability of devices based on the implementation of classical methods of analysis. The authors used neural network methods for the analysis of vibro-signals, which made it possible to increase the reliability of diagnosing pipeline systems. The present work considers a method of neural network analysis of amplitude-frequency measurements in pipelines to identify the presence of a defect and further clarify its variety. Document type: Article

Abstract

The objective of this study is to predict the degree of danger to the human body from motion information such as acceleration, velocity and displacement during a collision between a car and a human body. As a preliminary step, the maximum bending moment that occurs in the leg was predicted using a convolutional neural network. The responses which are represented by learning data generated by 1D-CAE system. A number of training data sets are varied in order to show the enough number to predict. The predictor's accuracy is evaluated by the test data sets. We'd like to discuss necessisty of a total number of training data sets and effectiveness of data augmentation technique. In addition, the technique to utilize classification by the t-SNE method to improve accuracy is also examined. t-SNE is based on classification algorithm, however an engineering interpolation should be computed based on physical meanings and influential parameters.