Multi-view Car Research Articles

Path Planning Method of Rolling Brush of Car Washing Machine Based on Fractional Differentiation

The roller brush cleaning path of the gantry reciprocating automatic car washing machine is the key to determining the quality of the car wash. For the issue that the traditional method cannot accurately and reliably calculate the roller path, a rolling brush path planning scheme combined with fractional differential algorithm is proposed. By analysing the working form of the car washing machine and the appearance characteristics of the car, a multi-view car detection system is designed, and the car images are collected by using multiple cameras. The possibility of the path of each roller brush of the car washing machine is extracted from the contour information, and the contour curve is converted into the roller brush path in the form of coordinate points through software. Finally, the actual size of the car to be washed is calculated by the multi-view camera, and the average error between the calculation result and the actual result is 2.63%, which meets the operating conditions of the gantry reciprocating automatic car washing machine.

Joint 3-D Shape Estimation and Landmark Localization From Monocular Cameras of Intelligent Vehicles

3-D reconstruction is at the core for many driving applications of Internet of Intelligent Vehicles. Previous works on reconstruction of a 3-D point shape commonly use a two-step framework. Precisely localizing a series of feature points in an image is performed on the first step. Then the second procedure attempts to fit the 3-D data to the observations to get the real 3-D shape. Such an approach has high time consumption, and easily gets stuck into local minimum. To address this problem, we propose a method to jointly estimate the global 3-D geometric structure of car and localize 2-D landmarks from a single viewpoint image. First, we represent the 3-D shape with a set of predefined shape bases, while parametrizing it by the coefficients of the linear combination of them. Second, we adopt a cascaded regression framework to regress the global shape encoded by the prior bases, by jointly minimizing the appearance and shape fitting differences. The position fitting item can help cope with the description ambiguity of local appearance, and provide more information for 3-D reconstruction. We apply the proposed approach on a multiview car dataset. Experimental results demonstrate favorable improvements on pose estimation and shape prediction, compared with some previous methods.

Vehicle Re-Identification by Deep Hidden Multi-View Inference.

Vehicle re-identification (re-ID) is an area that has received far less attention in the computer vision community than the prevalent person re-ID. Possible reasons for this slow progress are the lack of appropriate research data and the special 3D structure of a vehicle. Previous works have generally focused on some specific views (e.g., front); but, these methods are less effective in realistic scenarios, where vehicles usually appear in arbitrary views to cameras. In this paper, we focus on the uncertainty of vehicle viewpoint in re-ID, proposing two end-to-end deep architectures: the Spatially Concatenated ConvNet and convolutional neural network (CNN)-LSTM bi-directional loop. Our models exploit the great advantages of the CNN and long short-term memory (LSTM) to learn transformations across different viewpoints of vehicles. Thus, a multi-view vehicle representation containing all viewpoints' information can be inferred from the only one input view, and then used for learning to measure distance. To verify our models, we also introduce a Toy Car RE-ID data set with images from multiple viewpoints of 200 vehicles. We evaluate our proposed methods on the Toy Car RE-ID data set and the public Multi-View Car, VehicleID, and VeRi data sets. Experimental results illustrate that our models achieve consistent improvements over the state-of-the-art vehicle re-ID approaches.

Hierarchical Sliding Slice Regression for Vehicle Viewing Angle Estimation

We propose a novel hierarchical sliding slice regression which in a coarse-to-fine manner represents global circular target space with a number of ordinally localized and overlapping subspaces. Our method is particularly suitable for visual regression problems where the regression target is circular (e.g., car viewing angle) and visual similarity inconsistent over the target space (e.g., repetitive appearance). A good application example is the camera-based car viewing angle estimation problem, where visual similarity of different views is highly inconsistent—front and back views and left and right side views are pair-wise similar, but appear at the far ends of the circular view angle space. In practice, the problem is even more complicated due to large visual variation of objects (e.g., different car models). We perform extensive experiments on the Lausanne Federal of Institute of Technology Multi-view Car and KITTI Data Sets as well as the Technische Universitat Darmstadt Multi-view Pedestrians Data Set and achieve superior performance as compared to the state-of-the-art algorithms.

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.