Refine
Document Type
- Conference Proceeding (19) (remove)
Language
- English (19)
Keywords
- 3D ship detection (1)
- Computer vision (1)
- Extended object tracking (1)
- Extension estimation (1)
- Finite-element (1)
- GPU (1)
- Gaussian processes (1)
- Inverse perspective (1)
- Learning to cluster (1)
- Lidar (1)
Institute
- Institut für Optische Systeme - IOS (19) (remove)
Incremental one-class learning using regularized null-space training for industrial defect detection
(2024)
One-class incremental learning is a special case of class-incremental learning, where only a single novel class is incrementally added to an existing classifier instead of multiple classes. This case is relevant in industrial defect detection scenarios, where novel defects usually appear during operation. Existing rolled-out classifiers must be updated incrementally in this scenario with only a few novel examples. In addition, it is often required that the base classifier must not be altered due to approval and warranty restrictions. While simple finetuning often gives the best performance across old and new classes, it comes with the drawback of potentially losing performance on the base classes (catastrophic forgetting [1]). Simple prototype approaches [2] work without changing existing weights and perform very well when the classes are well separated but fail dramatically when not. In theory, null-space training (NSCL) [3] should retain the basis classifier entirely, as parameter updates are restricted to the null space of the network with respect to existing classes. However, as we show, this technique promotes overfitting in the case of one-class incremental learning. In our experiments, we found that unconstrained weight growth in null space is the underlying issue, leading us to propose a regularization term (R-NSCL) that penalizes the magnitude of amplification. The regularization term is added to the standard classification loss and stabilizes null-space training in the one-class scenario by counteracting overfitting. We test the method’s capabilities on two industrial datasets, namely AITEX and MVTec, and compare the performance to state-of-the-art algorithms for class-incremental learning.
Motion estimation is an essential element for autonomous vessels. It is used e.g. for lidar motion compensation as well as mapping and detection tasks in a maritime environment. Because the use of gyroscopes is not reliable and a high performance inertial measurement unit is quite expensive, we present an approach for visual pitch and roll estimation that utilizes a convolutional neural network for water segmentation, a stereo system for reconstruction and simple geometry to estimate pitch and roll. The algorithm is validated on a novel, publicly available dataset recorded at Lake Constance. Our experiments show that the pitch and roll estimator provides accurate results in comparison to an Xsens IMU sensor. We can further improve the pitch and roll estimation by sensor fusion with a gyroscope. The algorithm is available in its implementation as a ROS node.
Random matrices are used to filter the center of gravity (CoG) and the covariance matrix of measurements. However, these quantities do not always correspond directly to the position and the extent of the object, e.g. when a lidar sensor is used.In this paper, we propose a Gaussian processes regression model (GPRM) to predict the position and extension of the object from the filtered CoG and covariance matrix of the measurements. Training data for the GPRM are generated by a sampling method and a virtual measurement model (VMM). The VMM is a function that generates artificial measurements using ray tracing and allows us to obtain the CoG and covariance matrix that any object would cause. This enables the GPRM to be trained without real data but still be applied to real data due to the precise modeling in the VMM. The results show an accurate extension estimation as long as the reality behaves like the modeling and e.g. lidar measurements only occur on the side facing the sensor.
Targetless Lidar-camera registration is a repeating task in many computer vision and robotics applications and requires computing the extrinsic pose of a point cloud with respect to a camera or vice-versa. Existing methods based on learning or optimization lack either generalization capabilities or accuracy. Here, we propose a combination of pre-training and optimization using a neural network-based mutual information estimation technique (MINE [1]). This construction allows back-propagating the gradient to the calibration parameters and enables stochastic gradient descent. To ensure orthogonality constraints with respect to the rotation matrix we incorporate Lie-group techniques. Furthermore, instead of optimizing on entire images, we operate on local patches that are extracted from the temporally synchronized projected Lidar points and camera frames. Our experiments show that this technique not only improves over existing techniques in terms of accuracy, but also shows considerable generalization capabilities towards new Lidar-camera configurations.
Multi-Dimensional Connectionist Classification is amethod for weakly supervised training of Deep Neural Networksfor segmentation-free multi-line offline handwriting recognition.MDCC applies Conditional Random Fields as an alignmentfunction for this task. We discuss the structure and patterns ofhandwritten text that can be used for building a CRF. Since CRFsare cyclic graphical models, we have to resort to approximateinference when calculating the alignment of multi-line text duringtraining, here in the form of Loopy Belief Propagation. This workconcludes with experimental results for transcribing small multi-line samples from the IAM Offline Handwriting DB which showthat MDCC is a competitive methodology.
Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BDNNs, do provide uncertainty measures. However, BDNNs are slow during test time because they rely on a sampling approach. Here we present a single shot MC dropout approximation that preserves the advantages of BDNNs without being slower than a DNN. Our approach is to analytically approximate for each layer in a fully connected network the expected value and the variance of the MC dropout signal. We evaluate our approach on different benchmark datasets and a simulated toy example. We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.
Three-dimensional ship localization with only one camera is a challenging task due to the loss of depth information caused by perspective projection. In this paper, we propose a method to measure distances based on the assumption that ships lie on a flat surface. This assumption allows to recover depth from a single image using the principle of inverse perspective. For the 3D ship detection task, we use a hybrid approach that combines image detection with a convolutional neural network, camera geometry and inverse perspective. Furthermore, a novel calculation of object height is introduced. Experiments show that the monocular distance computation works well in comparison to a Velodyne lidar. Due to its robustness, this could be an easy-to-use baseline method for detection tasks in navigation systems.
Fast and reliable acquisition of truth data for document analysis using cyclic suggest algorithms
(2019)
In document analysis the availability of ground truth data plays a crucial role for the success of a project. This is even more true at the rise of new deep learning methods which heavily rely on the availability of training data. But even for traditional, hand crafted algorithms that are not trained on data, reliable test data is important for the improvement and evaluation of the methods. Because ground truth acquisition is expensive and time consuming, semi-automatic methods are introduced which make use of suggestions coming from document analysis systems. The interaction between the human operator and the automatic analysis algorithms is the key to speed up the process while improving the quality of the data. The final confirmation of data may always be done by the human operator. This paper demonstrates a use case for acquisition of truth data in a mail processing system. It shows why a new, extended view on truth data is necessary in development and engineering of such systems. An overview over the tool and the data handling is given, the advantages in the workflow are shown, and consequences for the construction of analysis algorithms are discussed. It can be shown that the interplay between suggest algorithms and human operator leads to very fast truth data capturing. The surprising finding is the fact that if multiple suggest algorithms circularly depend on data, they are especially effective in terms of speed and accuracy.
In this paper we present a method using deep learning to compute parametrizations for B-spline curve approximation. Existing methods consider the computation of parametric values and a knot vector as separate problems. We propose to train interdependent deep neural networks to predict parametric values and knots. We show that it is possible to include B-spline curve approximation directly into the neural network architecture. The resulting parametrizations yield tight approximations and are able to outperform state-of-the-art methods.
Deep neural networks have been successfully applied to problems such as image segmentation, image super-resolution, coloration and image inpainting. In this work we propose the use of convolutional neural networks (CNN) for image inpainting of large regions in high-resolution textures. Due to limited computational resources processing high-resolution images with neural networks is still an open problem. Existing methods separate inpainting of global structure and the transfer of details, which leads to blurry results and loss of global coherence in the detail transfer step. Based on advances in texture synthesis using CNNs we propose patch-based image inpainting by a single network topology that is able to optimize for global as well as detail texture statistics. Our method is capable of filling large inpainting regions, oftentimes exceeding quality of comparable methods for images of high-resolution (2048x2048px). For reference patch look-up we propose to use the same summary statistics that are used in the inpainting process.
We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1≤k≤kmax, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this “learning to cluster” and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.
Optical surface inspection: A novelty detection approach based on CNN-encoded texture features
(2018)
In inspection systems for textured surfaces, a reference texture is typically known before novel examples are inspected. Mostly, the reference is only available in a digital format. As a consequence, there is no dataset of defective examples available that could be used to train a classifier. We propose a texture model approach to novelty detection. The texture model uses features encoded by a convolutional neural network (CNN) trained on natural image data. The CNN activations represent the specific characteristics of the digital reference texture which are learned by a one-class classifier. We evaluate our novelty detector in a digital print inspection scenario. The inspection unit is based on a camera array and a flashing light illumination which allows for inline capturing of multichannel images at a high rate. In order to compare our results to manual inspection, we integrated our inspection unit into an industrial single-pass printing system.
Offline handwriting recognition systems often use LSTM networks, trained with line- or word-images. Multi-line text makes it necessary to use segmentation to explicitly obtain these images. Skewed, curved, overlapping, incorrectly written text, or noise can lead to errors during segmentation of multi-line text and reduces the overall recognition capacity of the system. Last year has seen the introduction of deep learning methods capable of segmentation-free recognition of whole paragraphs. Our method uses Conditional Random Fields to represent text and align it with the network output to calculate a loss function for training. Experiments are promising and show that the technique is capable of training a LSTM multi-line text recognition system.
Algorithms for calculating the string edit distance are used in e.g. information retrieval and document analysis systems or for evaluation of text recognizers. Text recognition based on CTC-trained LSTM networks includes a decoding step to produce a string, possibly using a language model, and evaluation using the string edit distance. The decoded string can further be used as a query for database search, e.g. in document retrieval. We propose to closely integrate dictionary search with text recognition to train both combined in a continuous fashion. This work shows that LSTM networks are capable of calculating the string edit distance while allowing for an exchangeable dictionary to separate learned algorithm from data. This could be a step towards integrating text recognition and dictionary search in one deep network.
Deep neural networks have become a veritable alternative to classic speaker recognition and clustering methods in recent years. However, while the speech signal clearly is a time series, and despite the body of literature on the benefits of prosodic (suprasegmental) features, identifying voices has usually not been approached with sequence learning methods. Only recently has a recurrent neural network (RNN) been successfully applied to this task, while the use of convolutional neural networks (CNNs) (that are not able to capture arbitrary time dependencies, unlike RNNs) still prevails. In this paper, we show the effectiveness of RNNs for speaker recognition by improving state of the art speaker clustering performance and robustness on the classic TIMIT benchmark. We provide arguments why RNNs are superior by experimentally showing a “sweet spot” of the segment length for successfully capturing prosodic information that has been theoretically predicted in previous work.
Visualization-Assisted Development of Deep Learning Models in Offline Handwriting Recognition
(2018)
Deep learning is a field of machine learning that has been the focus of active research and successful applications in recent years. Offline handwriting recognition is one of the research fields and applications were deep neural networks have shown high accuracy. Deep learning models and their training pipeline show a large amount of hyper-parameters in their data selection, transformation, network topology and training process that are sometimes interdependent. This increases the overall difficulty and time necessary for building and training a model for a specific data set and task at hand. This work proposes a novel visualization-assisted workflow that guides the model developer through the hyper-parameter search in order to identify relevant parameters and modify them in a meaningful way. This decreases the overall time necessary for building and training a model. The contributions of this work are a workflow for hyper-parameter search in offline handwriting recognition and a heat map based visualization technique for deep neural networks in multi-line offline handwriting recognition. This work applies to offline handwriting recognition, but the general workflow can possibly be adapted to other tasks as well.
We analyse the results of a finite element simulation of a macroscopic model, which describes the movement of a crowd, that is considered as a continuum. A new formulation based on the macroscopic model from Hughes [2] is given. We present a stable numerical algorithm by approximating with a viscosity solution. The fundamental setting is given by an arbitrary domain that can contain several obstacles, several entries and must have at least one exit. All pedestrians have the goal to leave the room as quickly as possible. Nobody prefers a particular exit.
Using multi-camera matching techniques for 3d reconstruction there is usually the trade-off between the quality of the computed depth map and the speed of the computations. Whereas high quality matching methods take several seconds to several minutes to compute a depth map for one set of images, real-time methods achieve only low quality results. In this paper we present a multi-camera matching method that runs in real-time and yields high resolution depth maps. Our method is based on a novel multi-level combination of normalized cross correlation, deformed matching windows based on the multi-level depth map information, and sub-pixel precise disparity maps. The whole process is implemented completely on the GPU. With this approach we can process four 0.7 megapixel images in 129 milliseconds to a full resolution 3d depth map. Our technique is tailored for the recognition of non-technical shapes, because our target application is face recognition.