University of Nebraska Omaha（内布拉斯加大学奥马哈分校）；New Jersey Institute of Technology（新泽西理工学院）
Nishan Khatri, Agnibh Dasgupta, Yucong Shen, Xin Zhong, Frank Y. Shih
备注：
This paper has been accepted for publication by the 2022 International Conference on Computational Science & Computational Intelligence (CSCI'22), Research Track on Signal & Image Processing, Computer Vision & Pattern Recognition
Incorporating geometric transformations that reflect the relative position changes between an observer and an object into computer vision and deep learning models has attracted much attention in recent years. However, the existing proposals mainly focus on the affine transformation that is insufficient to reflect such geometric position changes. Furthermore, current solutions often apply a neural network module to learn a single transformation matrix, which not only ignores the importance of multi-view analysis but also includes extra training parameters from the module apart from the transformation matrix parameters that increase the model complexity. In this paper, a perspective transformation layer is proposed in the context of deep learning. The proposed layer can learn homography, therefore reflecting the geometric positions between observers and objects. In addition, by directly training its transformation matrices, a single proposed layer can learn an adjustable number of multiple viewpoints without considering module parameters. The experiments and evaluations confirm the superiority of the proposed layer.
Chalmers University of Technology（查尔姆斯理工大学）；Umeå University（于默奥大学）
We characterize the class of image plane transformations which realize rigid camera motions and call these transformations `rigidity preserving'. In particular, 2D translations of pinhole images are not rigidity preserving. Hence, when using CNNs for 3D inference tasks, it can be beneficial to modify the inductive bias from equivariance towards translations to equivariance towards rigidity preserving transformations. We investigate how equivariance with respect to rigidity preserving transformations can be approximated in CNNs, and test our ideas on both 6D object pose estimation and visual lo…
State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）
Image stitching algorithms often adopt the global transformation, such as homography, and work well for planar scenes or parallax free camera motions. However, these conditions are easily violated in practice. With casual camera motions, variable taken views, large depth change, or complex structures, it is a challenging task for stitching these images. The global transformation model often provides dreadful stitching results, such as misalignments or projective distortions, especially perspective distortion. To this end, we suggest a perspective-preserving warping for image stitching, which s…
Department of Computer Science（计算机科学系）；University of Maryland, College Park（马里兰大学帕克分校）
Machine learning models that are developed with invariance to certain types of data transformations have demonstrated superior generalization performance in practice. However, the underlying mechanism that explains why invariance leads to better generalization is not well-understood, limiting our ability to select appropriate data transformations for a given dataset. This paper studies the generalization benefit of model invariance by introducing the sample cover induced by transformations, i.e., a representative subset of a dataset that can approximately recover the whole dataset using transf…
Detection and tracking of vehicles captured by traffic surveillance cameras is a key component of intelligent transportation systems. We present an improved version of our algorithm for detection of 3D bounding boxes of vehicles, their tracking and subsequent speed estimation. Our algorithm utilizes the known geometry of vanishing points in the surveilled scene to construct a perspective transformation. The transformation enables an intuitive simplification of the problem of detecting 3D bounding boxes to detection of 2D bounding boxes with one additional parameter using a standard 2D object d…
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Incorporating multiple camera views for detection alleviates the impact of occlusions in crowded scenes. In a multiview system, we need to answer two important questions when dealing with ambiguities that arise from occlusions. First, how should we aggregate cues from the multiple views? Second, how should we aggregate unreliable 2D and 3D spatial information that has been tainted by occlusions? To address these questions, we propose a novel multiview detection system, MVDet. For multiview aggregation, existing methods combine anchor box features from the image plane, which potentially limits …
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；PhiGent Robotics（鉴智机器人）
Autonomous driving requires accurate and detailed Bird's Eye View (BEV) semantic segmentation for decision making, which is one of the most challenging tasks for high-level scene perception. Feature transformation from frontal view to BEV is the pivotal technology for BEV semantic segmentation. Existing works can be roughly classified into two categories, i.e., Camera model-Based Feature Transformation (CBFT) and Camera model-Free Feature Transformation (CFFT). In this paper, we empirically analyze the vital differences between CBFT and CFFT. The former transforms features based on the flat-wo…
UC San Diego（加州大学圣地亚哥分校）；Cyprus International University（塞浦路斯国际大学）；the Hong Kong University of Science and Technology（香港科技大学）；University of Thessaloniki（塞萨洛尼基大学）
Potholes are one of the most common forms of road damage, which can severely affect driving comfort, road safety and vehicle condition. Pothole detection is typically performed by either structural engineers or certified inspectors. This task is, however, not only hazardous for the personnel but also extremely time-consuming. This paper presents an efficient pothole detection algorithm based on road disparity map estimation and segmentation. We first generalize the perspective transformation by incorporating the stereo rig roll angle. The road disparities are then estimated using semi-global m…
Accurate detection of lane and road markings is a task of great importance for intelligent vehicles. In existing approaches, the detection accuracy often degrades with the increasing distance. This is due to the fact that distant lane and road markings occupy a small number of pixels in the image, and scales of lane and road markings are inconsistent at various distances and perspectives. The Inverse Perspective Mapping (IPM) can be used to eliminate the perspective distortion, but the inherent interpolation can lead to artifacts especially around distant lane and road markings and thus has a …
Video-based glint-free eye tracking commonly estimates gaze direction based on the pupil center. The boundary of the pupil is fitted with an ellipse and the euclidean center of the ellipse in the image is taken as the center of the pupil. However, the center of the pupil is generally not mapped to the center of the ellipse by the projective camera transformation. This error resulting from using a point that is not the true center of the pupil directly affects eye tracking accuracy. We investigate the underlying geometric problem of determining the center of a circular object based on its proje…
Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically, we propose a model with two latent spaces: one that represents spatial transformations of the input data, and another that represents the transformed data. We find that the latter naturally captures the intrinsic appearance of the data. To realize the generative model, we propose a Variationally Inferred Transformational Autoencoder (VITAE) that incorporates…
Shanghai Jiao Tong University（上海交通大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；the Hong Kong University of Science and Technology（香港科技大学）
Semantic road region segmentation is a high-level task, which paves the way towards road scene understanding. This paper presents a residual network trained for semantic road segmentation. Firstly, we represent the projections of road disparities in the v-disparity map as a linear model, which can be estimated by optimizing the v-disparity map using dynamic programming. This linear model is then utilized to reduce the redundant information in the left and right road images. The right image is also transformed into the left perspective view, which greatly enhances the road surface similarity be…
Local processing is an essential feature of CNNs and other neural network architectures - it is one of the reasons why they work so well on images where relevant information is, to a large extent, local. However, perspective effects stemming from the projection in a conventional camera vary for different global positions in the image. We introduce Perspective Crop Layers (PCLs) - a form of perspective crop of the region of interest based on the camera geometry - and show that accounting for the perspective consistently improves the accuracy of state-of-the-art 3D pose reconstruction methods. P…
Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Nokia Research Center (NRC)（诺基亚研究中心）
Observational data usually comes with a multimodal nature, which means that it can be naturally represented by a multi-layer graph whose layers share the same set of vertices (users) with different edges (pairwise relationships). In this paper, we address the problem of combining different layers of the multi-layer graph for improved clustering of the vertices compared to using layers independently. We propose two novel methods, which are based on joint matrix factorization and graph regularization framework respectively, to efficiently combine the spectrum of the multiple graph layers, namely…
Learning features invariant to arbitrary transformations in the data is a requirement for any recognition system, biological or artificial. It is now widely accepted that simple cells in the primary visual cortex respond to features while the complex cells respond to features invariant to different transformations. We present a novel two-layered feedforward neural model that learns features in the first layer by spatial spherical clustering and invariance to transformations in the second layer by temporal spherical clustering. Learning occurs in an online and unsupervised manner following the …
We study the intrinsic transformation of feature maps across convolutional network layers with explicit top-down control. To this end, we develop top-down feature transformer (TFT), under controllable parameters, that are able to account for the hidden layer transformation while maintaining the overall consistency across layers. The learned generators capture the underlying feature transformation processes that are independent of particular training images. Our proposed TFT framework brings insights to and helps the understanding of, an important problem of studying the CNN internal feature re…
Baidu Research（百度研究院）；University of Technology Sydney（悉尼科技大学）
In this work, we propose a generally applicable transformation unit for visual recognition with deep convolutional neural networks. This transformation explicitly models channel relationships with explainable control variables. These variables determine the neuron behaviors of competition or cooperation, and they are jointly optimized with the convolutional weight towards more accurate recognition. In Squeeze-and-Excitation (SE) Networks, the channel relationships are implicitly learned by fully connected layers, and the SE block is integrated at the block-level. We instead introduce a channel…
University of Washington（华盛顿大学）；Google Brain（谷歌大脑）
Data augmentations are important ingredients in the recipe for training robust neural networks, especially in computer vision. A fundamental question is whether neural network features encode data augmentation transformations. To answer this question, we introduce a systematic approach to investigate which layers of neural networks are the most predictive of augmentation transformations. Our approach uses features in pre-trained vision models with minimal additional processing to predict common properties transformed by augmentation (scale, aspect ratio, hue, saturation, contrast, and brightne…
Georgetown University Medical Center（乔治城大学医学中心）；Virginia Tech（弗吉尼亚理工大学）；Harbin Institute of Technology（哈尔滨工业大学）
Mathematically speaking, a transformationally invariant operator, such as a transformationally identical (TI) matrix kernel (i.e., K= T{K}), commutes with the transformation (T{.}) itself when they operate on the first operand matrix. We found that by consistently applying the same type of TI kernels in a convolutional neural networks (CNN) system, the commutative property holds throughout all layers of convolution processes with and without involving an activation function and/or a 1D convolution across channels within a layer. We further found that any CNN possessing the same TI kernel prope…
Huazhong University of Science and Technology（华中科技大学）；Baidu Inc.（百度公司）
Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability. It is challenging to estimate the BEV semantic maps from monocular images due to the spatial gap, since it is implicitly required to realize both the perspective-to-BEV transformation and segmentation. We present a novel two-stage Geometry Prior-based Transformation framework named GitNet, consisting of (i) the geometry-guided pre-alignment and (ii) ray-based transformer. In the first stage, we decouple the BEV segmentation into the perspective image segmentation and g…
