Typical Structure-from-Motion (SfM) pipelines rely on finding correspondences across images, recovering the projective structure of the observed scene and upgrading it to a metric frame using camera self-calibration constraints. Solving each problem is mainly carried out independently from the others. For instance, camera self-calibration generally assumes correct matches and a good projective reconstruction have been obtained. In this paper, we propose a unified SfM method, in which the matching process is supported by self-calibration constraints. We use the idea that good matches should yield a valid calibration. In this process, we make use of the Dual Image of Absolute Quadric projection equations within a multiview correspondence framework, in order to obtain robust matching from a set of putative correspondences. The matching process classifies points as inliers or outliers, which is learned in an unsupervised manner using a deep neural network. Together with theoretical reasoning why the self-calibration constraints are necessary, we show experimental results demonstrating robust multiview matching and accurate camera calibration by exploiting these constraints.
Augmented reality devices require multiple sensors to perform various tasks such as localization and tracking. Currently, popular cameras are mostly frame-based (e.g. RGB and Depth) which impose a high data bandwidth and power usage. With the necessity for low power and more responsive augmented reality systems, using solely frame-based sensors imposes limits to the various algorithms that needs high frequency data from the environement. As such, event-based sensors have become increasingly popular due to their low power, bandwidth and latency, as well as their very high frequency data acquisition capabilities. In this paper, we propose, for the first time, to use an event-based camera to increase the speed of 3D object tracking in 6 degrees of freedom. This application requires handling very high object speed to convey compelling AR experiences. To this end, we propose a new system which combines a recent RGB-D sensor (Kinect Azure) with an event camera (DAVIS346). We develop a deep learning approach, which combines an existing RGB-D network along with a novel event-based network in a cascade fashion, and demonstrate that our approach significantly improves the robustness of a state-of-the-art frame-based 6-DOF object tracker using our RGB-D-E pipeline.
Lidar based 3D object detection and classification tasks are essential for autonomous driving(AD). A lidar sensor can provide the 3D point cloud data reconstruction of the surrounding environment. However, real time detection in 3D point clouds still needs a strong algorithmic. This paper proposes a 3D object detection method based on point cloud and image which consists of there parts.(1)Lidar-camera calibration and undistorted image transformation. (2)YOLO-based detection and PointCloud extraction, (3)K-means based point cloud segmentation and detection experiment test and evaluation in depth image. In our research, camera can capture the image to make the Real-time 2D object detection by using YOLO, we transfer the bounding box to node whose function is making 3d object detection on point cloud data from Lidar. By comparing whether 2D coordinate transferred from the 3D point is in the object bounding box or not can achieve High-speed 3D object recognition function in GPU. The accuracy and precision get imporved after k-means clustering in point cloud. The speed of our detection method is a advantage faster than PointNet.
The goal of the proposed method is to directly obtain a pose matrix of a known rectangular target, without estimation, using geometric techniques. This method is specifically tailored for real-time, extreme imaging setups exceeding 180{\deg} field of view, such as a fish-eye camera view. The introduced algorithm employs geometric algebra to determine the pose for a pair of coplanar parallel lines (ideally a tangent pair as in a rectangle). This is achieved by computing vanishing points on a visual unit sphere, which correspond to pose matrix vectors. The algorithm can determine pose for an extremely distorted view source without prior rectification, owing to a visual-sphere perspective model mapping of view coordinates. Mapping can be performed using either a perspective map lookup or a parametric universal perspective distortion model, which is also presented in this paper. The outcome is a robust pose matrix computation that can be executed on an embedded system using a microcontroller, offering high accuracy and low latency. This method can be further extended to a cubic target setup for comprehensive camera calibration. It may also prove valuable in other applications requiring low latency and extreme viewing angles.
The most prevalent routine for camera calibration is based on the detection of well-defined feature points on a purpose-made calibration artifact. These could be checkerboard saddle points, circles, rings or triangles, often printed on a planar structure. The feature points are first detected and then used in a nonlinear optimization to estimate the internal camera parameters.We propose a new method for camera calibration using the principle of inverse rendering. Instead of relying solely on detected feature points, we use an estimate of the internal parameters and the pose of the calibration object to implicitly render a non-photorealistic equivalent of the optical features. This enables us to compute pixel-wise differences in the image domain without interpolation artifacts. We can then improve our estimate of the internal parameters by minimizing pixel-wise least-squares differences. In this way, our model optimizes a meaningful metric in the image space assuming normally distributed noise characteristic for camera sensors.We demonstrate using synthetic and real camera images that our method improves the accuracy of estimated camera parameters as compared with current state-of-the-art calibration routines. Our method also estimates these parameters more robustly in the presence of noise and in situations where the number of calibration images is limited.
The majority of learning-based semantic segmentation methods are optimized for daytime scenarios and favorable lighting conditions. Real-world driving scenarios, however, entail adverse environmental conditions such as nighttime illumination or glare which remain a challenge for existing approaches. In this work, we propose a multimodal semantic segmentation model that can be applied during daytime and nighttime. To this end, besides RGB images, we leverage thermal images, making our network significantly more robust. We avoid the expensive annotation of nighttime images by leveraging an existing daytime RGB-dataset and propose a teacher-student training approach that transfers the dataset's knowledge to the nighttime domain. We further employ a domain adaptation method to align the learned feature spaces across the domains and propose a novel two-stage training scheme. Furthermore, due to a lack of thermal data for autonomous driving, we present a new dataset comprising over 20,000 time-synchronized and aligned RGB-thermal image pairs. In this context, we also present a novel target-less calibration method that allows for automatic robust extrinsic and intrinsic thermal camera calibration. Among others, we employ our new dataset to show state-of-the-art results for nighttime semantic segmentation.
In this work, we present an effective multi-view approach to closed-loop end-to-end learning of precise manipulation tasks that are 3D in nature. Our method learns to accomplish these tasks using multiple statically placed but uncalibrated RGB camera views without building an explicit 3D representation such as a pointcloud or voxel grid. This multi-camera approach achieves superior task performance on difficult stacking and insertion tasks compared to single-view baselines. Single view robotic agents struggle from occlusion and challenges in estimating relative poses between points of interest. While full 3D scene representations (voxels or pointclouds) are obtainable from registered output of multiple depth sensors, several challenges complicate operating off such explicit 3D representations. These challenges include imperfect camera calibration, poor depth maps due to object properties such as reflective surfaces, and slower inference speeds over 3D representations compared to 2D images. Our use of static but uncalibrated cameras does not require camera-robot or camera-camera calibration making the proposed approach easy to setup and our use of \textit{sensor dropout} during training makes it resilient to the loss of camera-views after deployment.
We propose an easy-to-use non-overlapping camera calibration method. First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames. Next, the pose between cameras are estimated. Instead of using a batch method, we propose an on-line method of the inter-camera pose estimation. Furthermore, we implement the entire procedure on a computation graph. Experiments with simulations and the KITTI dataset show the proposed method to be effective in simulation.
Accurate object segmentation is a crucial task in the context of robotic manipulation. However, creating sufficient annotated training data for neural networks is particularly time consuming and often requires manual labeling. To this end, we propose a simple, yet robust solution for learning to segment unknown objects grasped by a robot. Specifically, we exploit motion and temporal cues in RGB video sequences. Using optical flow estimation we first learn to predict segmentation masks of our given manipulator. Then, these annotations are used in combination with motion cues to automatically distinguish between background, manipulator and unknown, grasped object. In contrast to existing systems our approach is fully self-supervised and independent of precise camera calibration, 3D models or potentially imperfect depth data. We perform a thorough comparison with alternative baselines and approaches from literature. The object masks and views are shown to be suitable training data for segmentation networks that generalize to novel environments and also allow for watertight 3D reconstruction.
The scalability and complexity of deep learning models remains a key issue in many of visual recognition applications like, e.g., video surveillance, where fine tuning with labeled image data from each new camera is required to reduce the domain shift between videos captured from the source domain, e.g., a laboratory setting, and the target domain, i.e, an operational environment. In many video surveillance applications, like face recognition (FR) and person re-identification, a pair-wise matcher is used to assign a query image captured using a video camera to the corresponding reference images in a gallery. The different configurations and operational conditions of video cameras can introduce significant shifts in the pair-wise distance distributions, resulting in degraded recognition performance for new cameras. In this paper, a new deep domain adaptation (DA) method is proposed to adapt the CNN embedding of a Siamese network using unlabeled tracklets captured with a new video cameras. To this end, a dual-triplet loss is introduced for metric learning, where two triplets are constructed using video data from a source camera, and a new target camera. In order to constitute the dual triplets, a mutual-supervised learning approach is introduced where the source camera acts as a teacher, providing the target camera with an initial embedding. Then, the student relies on the teacher to iteratively label the positive and negative pairs collected during, e.g., initial camera calibration. Both source and target embeddings continue to simultaneously learn such that their pair-wise distance distributions become aligned. For validation, the proposed metric learning technique is used to train deep Siamese networks under different training scenarios, and is compared to state-of-the-art techniques for still-to-video FR on the COX-S2V and a private video-based FR dataset.
Accurately calibrating light field camera is essential to its applications. Rapid progress has been made in this area in the past decades. In this paper, detailed analysis was first performed towards the state of the art projection models for calibration which were further interpreted in three representations, including the correspondence between rays and pixels, 3D physical points and pixels and between 3D physical points and 3D signal structure of the captured light field. Based on the analysis, parameters in the projection model were grouped into direction parameter set and depth parameter set. A two-step calibration method was then proposed with each step dealing with each set of parameters. The proposed method is able to reuse traditional camera calibration methods for the direction parameter set. A simply raw image-based calibration of depth parameter set was further proposed. Systematic validations were conducted to evaluate the performance of the proposed calibration method. Experimental results show that the accuracy and robustness of the proposed method outperforms its counterparts under various benchmark criteria.
Achieving color constancy between and within images, i.e., minimizing the color difference between the same object imaged under nonuniform and varied illuminations is crucial for computer vision tasks such as colorimetric analysis and object recognition. Most current methods attempt to solve this by illumination correction on perceptual color spaces. In this paper, we proposed two pixel-wise algorithms to achieve relative color constancy by working under the spectral domain. That is, the proposed algorithms map each pixel to the reflectance ratio of objects appeared in the scene and perform illumination correction in this spectral domain. Also, we proposed a camera calibration technique that calculates the characteristics of a camera without the need of a standard reference. We show that both of the proposed algorithms achieved the best performance on nonuniform illumination correction and relative illumination matching respectively compared to the benchmarked algorithms.
Camera calibration is an essential first step in setting up 3D Computer Vision systems. Commonly used parametric camera models are limited to a few degrees of freedom and thus often do not optimally fit to complex real lens distortion. In contrast, generic camera models allow for very accurate calibration due to their flexibility. Despite this, they have seen little use in practice. In this paper, we argue that this should change. We propose a calibration pipeline for generic models that is fully automated, easy to use, and can act as a drop-in replacement for parametric calibration, with a focus on accuracy. We compare our results to parametric calibrations. Considering stereo depth estimation and camera pose estimation as examples, we show that the calibration error acts as a bias on the results. We thus argue that in contrast to current common practice, generic models should be preferred over parametric ones whenever possible. To facilitate this, we released our calibration pipeline at https://github.com/puzzlepaint/camera_calibration, making both easy-to-use and accurate camera calibration available to everyone.
Image-based 3D reconstruction or 3D photogrammetry of small-scale objects including insects and biological specimens is challenging due to the use of high magnification lens with inherent limited depth of field, and the object's fine structures and complex surface properties. Due to these challenges, traditional 3D reconstruction techniques cannot be applied without suitable image pre-processings. One such preprocessing technique is multifocus stacking that combines a set of partially focused images captured from the same viewing angle to create a single in-focus image. Traditional multifocus image capture uses a camera on a macro rail. Furthermore, the scale and shift are not properly considered by multifocus stacking techniques. As a consequence, the resulting in-focus images contain artifacts that violate perspective image formation. A 3D reconstruction using such images will fail to produce an accurate 3D model of the object. This paper shows how this problem can be solved effectively by a new multifocus stacking procedure which includes a new Fixed-Lens Multifocus Capture and camera calibration for image scale and shift. Initial experimental results are presented to confirm our expectation and show that the camera poses of fixed-lens images are at least 3-times less noisy than those of conventional moving lens images.
Robust and accurate camera calibration is essential for 3D reconstruction in light microscopy under circular motion. Conventional methods require either accurate key point matching or precise segmentation of the axial-view images. Both remain challenging because specimens often exhibit transparency/translucency in a light microscope. To address those issues, we propose a probabilistic inference based method for the camera calibration that does not require sophisticated image pre-processing. Based on 3D projective geometry, our method assigns a probability on each of a range of voxels that cover the whole object. The probability indicates the likelihood of a voxel belonging to the object to be reconstructed. Our method maximizes a joint probability that distinguishes the object from the background. Experimental results show that the proposed method can accurately recover camera configurations in both light microscopy and natural scene imaging. Furthermore, the method can be used to produce high-fidelity 3D reconstructions and accurate 3D measurements.
We present a simple yet effective end-to-end trainable deep network with geometry-inspired convolutional operators for detecting vanishing points in images. Traditional convolutional neural networks rely on aggregating edge features and do not have mechanisms to directly exploit the geometric properties of vanishing points as the intersections of parallel lines. In this work, we identify a canonical conic space in which the neural network can effectively compute the global geometric information of vanishing points locally, and we propose a novel operator named conic convolution that can be implemented as regular convolutions in this space. This new operator explicitly enforces feature extractions and aggregations along the structural lines and yet has the same number of parameters as the regular 2D convolution. Our extensive experiments on both synthetic and real-world datasets show that the proposed operator significantly improves the performance of vanishing point detection over traditional methods. The code and dataset have been made publicly available at https://github.com/zhou13/neurvps.
The homogeneous transformation between a LiDAR and monocular camera is required for sensor fusion tasks, such as SLAM. While determining such a transformation is not considered glamorous in any sense of the word, it is nonetheless crucial for many modern autonomous systems. Indeed, an error of a few degrees in rotation or a few percent in translation can lead to 20 cm translation errors at a distance of 5 m when overlaying a LiDAR image on a camera image. The biggest impediments to determining the transformation accurately are the relative sparsity of LiDAR point clouds and systematic errors in their distance measurements. This paper proposes (1) the use of targets of known dimension and geometry to ameliorate target pose estimation in face of the quantization and systematic errors inherent in a LiDAR image of a target, and (2) a fitting method for the LiDAR to monocular camera transformation that fundamentally assumes the camera image data is the most accurate information in one's possession.
This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. Inspired by OpenCV, Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations. Examples of classical vision problems implemented using our framework are provided including a benchmark comparing to existing vision libraries.
TagSLAM provides a convenient, flexible, and robust way of performing Simultaneous Localization and Mapping (SLAM) with AprilTag fiducial markers. By leveraging a few simple abstractions (bodies, tags, cameras), TagSLAM provides a front end to the GTSAM factor graph optimizer that makes it possible to rapidly design a range of experiments that are based on tags: full SLAM, extrinsic camera calibration with non-overlapping views, visual localization for ground truth, loop closure for odometry, pose estimation etc. We discuss in detail how TagSLAM initializes the factor graph in a robust way, and present loop closure as an application example. TagSLAM is a ROS based open source package and can be found at https://berndpfrommer.github.io/tagslam_web.
In this work we propose long wave infrared (LWIR) imagery as a viable supporting modality for semantic segmentation using learning-based techniques. We first address the problem of RGB-thermal camera calibration by proposing a passive calibration target and procedure that is both portable and easy to use. Second, we present PST900, a dataset of 894 synchronized and calibrated RGB and Thermal image pairs with per pixel human annotations across four distinct classes from the DARPA Subterranean Challenge. Lastly, we propose a CNN architecture for fast semantic segmentation that combines both RGB and Thermal imagery in a way that leverages RGB imagery independently. We compare our method against the state-of-the-art and show that our method outperforms them in our dataset.