Car Dataset Research Articles

Constrained Metric Learning by Permutation Inducing Isometries.

The choice of metric critically affects the performance of classification and clustering algorithms. Metric learning algorithms attempt to improve performance, by learning a more appropriate metric. Unfortunately, most of the current algorithms learn a distance function which is not invariant to rigid transformations of images. Therefore, the distances between two images and their rigidly transformed pair may differ, leading to inconsistent classification or clustering results. We propose to constrain the learned metric to be invariant to the geometry preserving transformations of images that induce permutations in the feature space. The constraint that these transformations are isometries of the metric ensures consistent results and improves accuracy. Our second contribution is a dimension reduction technique that is consistent with the isometry constraints. Our third contribution is the formulation of the isometry constrained logistic discriminant metric learning (IC-LDML) algorithm, by incorporating the isometry constraints within the objective function of the LDML algorithm. The proposed algorithm is compared with the existing techniques on the publicly available labeled faces in the wild, viewpoint-invariant pedestrian recognition, and Toy Cars data sets. The IC-LDML algorithm has outperformed existing techniques for the tasks of face recognition, person identification, and object classification by a significant margin.

Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation.

This paper presents a method for learning an And-Or model to represent context and occlusion for car detection and viewpoint estimation. The learned And-Or model represents car-to-car context and occlusion configurations at three levels: (i) spatially-aligned cars, (ii) single car under different occlusion configurations, and (iii) a small number of parts. The And-Or model embeds a grammar for representing large structural and appearance variations in a reconfigurable hierarchy. The learning process consists of two stages in a weakly supervised way (i.e., only bounding boxes of single cars are annotated). Firstly, the structure of the And-Or model is learned with three components: (a) mining multi-car contextual patterns based on layouts of annotated single car bounding boxes, (b) mining occlusion configurations between single cars, and (c) learning different combinations of part visibility based on CAD simulations. The And-Or model is organized in a directed and acyclic graph which can be inferred by Dynamic Programming. Secondly, the model parameters (for appearance, deformation and bias) are jointly trained using Weak-Label Structural SVM. In experiments, we test our model on four car detection datasets - the KITTI dataset [1], the PASCAL VOC2007 car dataset [2], and two self-collected car datasets, namely the Street-Parking car dataset and the Parking-Lot car dataset, and three datasets for car viewpoint estimation - the PASCAL VOC2006 car dataset [2], the 3D car dataset [3], and the PASCAL3D+ car dataset [4]. Compared with state-of-the-art variants of deformable part-based models and other methods, our model achieves significant improvement consistently on the four detection datasets, and comparable performance on car viewpoint estimation.

Learning 3D Object Templates by Quantizing Geometry and Appearance Spaces.

While 3D object-centered shape-based models are appealing in comparison with 2D viewer-centered appearance-based models for their lower model complexities and potentially better view generalizabilities, the learning and inference of 3D models has been much less studied in the recent literature due to two factors: i) the enormous complexities of 3D shapes in geometric space; and ii) the gap between 3D shapes and their appearances in images. This paper aims at tackling the two problems by studying an And-Or Tree (AoT) representation that consists of two parts: i) a geometry-AoT quantizing the geometry space, i.e. the possible compositions of 3D volumetric parts and 2D surfaces within the volumes; and ii) an appearance-AoT quantizing the appearance space, i.e. the appearance variations of those shapes in different views. In this AoT, an And-node decomposes an entity into constituent parts, and an Or-node represents alternative ways of decompositions. Thus it can express a combinatorial number of geometry and appearance configurations through small dictionaries of 3D shape primitives and 2D image primitives. In the quantized space, the problem of learning a 3D object template is transformed to a structure search problem which can be efficiently solved in a dynamic programming algorithm by maximizing the information gain. We focus on learning 3D car templates from the AoT and collect a new car dataset featuring more diverse views. The learned car templates integrate both the shape-based model and the appearance-based model to combine the benefits of both. In experiments, we show three aspects: 1) the AoT is more efficient than the frequently used octree method in space representation; 2) the learned 3D car template matches the state-of-the art performances on car detection and pose estimation in a public multi-view car dataset; and 3) in our new dataset, the learned 3D template solves the joint task of simultaneous object detection, pose/view estimation, and part localization. It can generalize over unseen views and performs better than the version5 of the DPM model in terms of object detection and semantic part localization.

Hybrid Approach for Detection and Recognition of Vehicles

On road vehicles have increased in numbers and monitoring them is a challenging task. In common areas of public crowd people and vehicles are common objects for monitoring. The proposed system aims at detecting number plate information indicating the possibility for security relevant issues. Existing system performs recognition mainly by using license plate alone. Addition of the features (logo, colour, shape) will increase the security of the system. Identification of the number plate region has been done by Blob detection method at the predefined aspect ratio. After detection, extraction of the number plate information using Eigen value regularization method. Further, two methodology included in this study are, identifying the tampered region in a car image either by extracting HoG feature in the spatial domain or block differences in DCT coefficients and their corresponding histogram in the transform domain respectively. Experimental results for the given car dataset describes the identification of the number plate region and tampered region quantitatively. The work presents detailed results of how the proposed approach gives better results using HoG approach. The approach gives good results in videos of cars recorded in frontal view in good lighting conditions. The paper in overall suggest a hybrid approach for detecting number plate information in cars taken in good lighting conditions.

Fine-tuning regression forests votes for object alignment in the wild.

In this paper, we propose a object alignment method that detects the landmarks of an object in 2D images. In the regression forests (RFs) framework, observations (patches) that are extracted at several image locations cast votes for the localization of several landmarks. We propose to refine the votes before accumulating them into the Hough space, by sieving and/or aggregating. In order to filter out false positive votes, we pass them through several sieves, each associated with a discrete or continuous latent variable. The sieves filter out votes that are not consistent with the latent variable in question, something that implicitly enforces global constraints. In order to aggregate the votes when necessary, we adjusts on-the-fly a proximity threshold by applying a classifier on middle-level features extracted from voting maps for the object landmark in question. Moreover, our method is able to predict the unreliability of an individual object landmark. This information can be useful for subsequent object analysis like object recognition. Our contributions are validated for two object alignment tasks, face alignment and car alignment, on data sets with challenging images collected in the wild, i.e., the Labeled Face in the Wild, the Annotated Facial Landmarks in the Wild, and the street scene car data set. We show that with the proposed approach, and without explicitly introducing shape models, we obtain performance superior or close to the state of the art for both tasks.

Asymmetric Pruning for Learning Cascade Detectors

Cascade classifiers are one of the most important contributions to real-time object detection. Nonetheless, there are many challenging problems arising in training cascade detectors. One common issue is that the node classifier is trained with a symmetric classifier. Having a low misclassification error rate does not guarantee an optimal node learning goal in cascade classifiers, i.e., an extremely high detection rate with a moderate false positive rate. In this work, we present a new approach to train an effective node classifier in a cascade detector. The algorithm is based on two key observations: 1) Redundant weak classifiers can be safely discarded; 2) The final detector should satisfy the asymmetric learning objective of the cascade architecture. To achieve this, we separate the classifier training into two steps: finding a pool of discriminative weak classifiers/features and training the final classifier by pruning weak classifiers which contribute little to the asymmetric learning criterion (asymmetric classifier construction). Our model reduction approach helps accelerate the learning time while achieving the pre-determined learning objective. Experimental results on both face and car data sets verify the effectiveness of the proposed algorithm. On the FDDB face data sets, our approach achieves the state-of-the-art performance, which demonstrates the advantage of our approach.

Contour level object detection with top-down information

This paper presents a contour level object detection approach. In contrast to conventional bounding box results, we give out the salient closed contour of the object, which provides a possibility of semantic analysis for the object. We get the salient closed contour with Ratio Contour algorithm. The top-down information needed by salient closed contour extraction is based on the well-known Bag-of-Features methodology. Our top-down information based contour extraction and completion is much more efficient and robust than many related approaches lack of the top-down information. We also propose a novel post-processing framework for object detection. With low threshold and a refined binary classifier, we can get stable high performance. We evaluate our approaches on UIUC cars dataset. We show that our approaches apparently improve the performance of object detections under clutter.

Espresso for Rule Mining

The Rule-based systems generate many of the redundant rules. Such rules are expensive especially in online systems. Currently, there are many of the available rule minimization techniques; however, they still suffer from many challenges in exploiting parallelism, load balancing, efficient memory usage, minimization of communication cost, efficient data, task decomposition and others. This paper introduces a new approach for minimizing association rules based on the adaptation of Espresso algorithm, used in reducing Boolean expressions. We believe that our proposed method is a simple and efficient method that supports a large number of input and output variables. The proposed method starts by the usage of binary encoding followed by the minimization. In the last step, data decoding is utilized generating the final rules. Such rule minimization could be used in many applications including the Wireless Sensor Networks collected data. For testing purposes, a car data set has been used and the results seem promising compared to the original rules

Document Classification Using Expectation Maximization with Semi Supervised Learning

As the amount of online document increases, the demand for document classification to aid the analysis and management of document is increasing. Text is cheap, but information, in the form of knowing what classes a document belongs to, is expensive. The main purpose of this paper is to explain the expectation maximization technique of data mining to classify the document and to learn how to improve the accuracy while using semi-supervised approach. Expectation maximization algorithm is applied with both supervised and semi-supervised approach. It is found that semi-supervised approach is more accurate and effective. The main advantage of semi supervised approach is “DYNAMICALLY GENERATION OF NEW CLASS”. The algorithm first trains a classifier using the labeled document and probabilistically classifies the unlabeled documents. The car dataset for the evaluation purpose is collected from UCI repository dataset in which some changes have been done from our side.

Picosecond spectral coherent anti-Stokes Raman scattering imaging with principal component analysis of meibomian glands

The lipid distribution in the mouse meibomian gland was examined with picosecond spectral anti-Stokes Raman scattering (CARS) imaging. Spectral CARS data sets were generated by imaging specific localized regions of the gland within tissue sections at consecutive Raman shifts in the CH(2) stretching vibrational range. Spectral differences between the location specific CARS spectra obtained in the lipid-rich regions of the acinus and the central duct were observed, which were confirmed with a Raman microspectroscopic analysis, and attributed to meibum lipid modifications within the gland. A principal component analysis of the spectral data set reveals changes in the CARS spectrum when transitioning from the acini to the central duct. These results demonstrate the utility of picosecond spectral CARS imaging combined with multivariate analysis for assessing differences in the distribution and composition of lipids in tissues.

Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object's location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the \chi;2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition.

Mean and dispersion modelling for policy claims costs

A model for the statistical analysis of the total amount of insurance paid out on a policy is developed and applied. The model simultaneously deals with the number of claims (zero or more) and the amount of each claim. The number of claims is from a Poisson-based discrete distribution. Individual claim sizes are from a continuous right skewed distribution. The resulting distribution of total claim size is a mixed discrete-continuous model, with positive probability of a zero claim. The means and dispersions of the claim frequency and claim size distribution are modeled in terms of risk factors. The model is applied to a car insurance data set.