Estimating Optical Flow with Streaming Perception and Changing Trend Aiming to Complex Scenarios

A number of proposed optical flow estimation algorithms for image motion analysis use only a few subsequent frames from an image sequence to perform calculation. Others, that use many frames, as is case in frequency and energy based, as well as in stochastic optical flow algorithms, are better suited for off-line work. We present our approach in adopting a classic gradient optical flow algorithm for on-line work over extended image sequence. Our experiments on the usual optical flow testing image sequences, consisting of few dozens of image frames show significant improvements in accuracy of the estimated velocity flow fields and in speed of computation. This is achieved by modification and integration of three basic processing phases: preparation of a limited spatio-temporal volume, estimation of velocity flow fields and post filtering of the flow fields. In the preparation phase we use efficient spatio-temporal filters for image smoothing. In the estimation phase a modified iterative solution that propagates results from previous calculation steps is used. Linear and nonlinear post filtering additionally improve optical flow estimates. The whole process is less sensitive to the aperture problem and produces more accurate flow field estimates than the original algorithm. It better copes with motion discontinuities as well. We evidence our achievements by a number of experiments on extended image sequences.

Optical flow is defined as the pattern of apparent motion of objects in a image sequence. Optical flow has many applications: control of automatic taking off and landing of an autonomous aircraft, video compression, noise suppression, motion compensation and many more. There are different methods to estimate the optical flow. Variational models are the most frequently used methods to estimate the optical flow. These methods states an energy model to estimate the optical flow and frequently linealizations are used. Theses linearizations causes that the optical flow estimation fails if the motion presents displacements larger than the size of the objects. Optical flow methods generally implies large execution time to be estimated. In this work is presented a method that incorporate, to the classical optical flow's Horn-Schunk method, exhaustive matchings. These exhaustive matchings improve the estimation to handle large displacements. The method was implemented in a Intel i7, 3.5 GHz, GPU GeForce NVidia GTX 980 Ti and also a standard web-cam. Using images of 320 240 pixels the implementation reaches 6 images per second, which means that it is able to run in real time.

Unsupervised deep learning methods have demonstrated an impressive performance for understanding the structure of 3D scene from videos. These data-based learning methods are able to learn the tasks, such as depth, ego-motion, and optical flow estimation. In this paper, we propose a novel unsupervised deep learning method to jointly estimate scene depth, camera ego-motion, and optical flow from stereo images. Consecutive stereo images are used to train the system. After training stage, the system is able to estimate dense depth map, camera 6D pose, and optical flow by using a sequence of monocular images. No labelled data set is required for training. The supervision signals for training three deep neural networks of the system come from various forms of image warping. Due to the use of optical flow, the impact caused by occlusions and moving objects on the estimation results is alleviated. Experiments on the KITTI and Cityscapes datasets show that the proposed system demonstrates a better performance in terms of accuracy in depth, ego-motion, and optical flow estimation.

In this paper, we propose UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption. UnOS significantly outperforms other state-of-the-art (SOTA) unsupervised approaches that treated the two tasks independently. Specifically, given two consecutive stereo image pairs from a video, UnOS estimates per-pixel stereo depth images, camera ego-motion and optical flow with three parallel CNNs. Based on these quantities, UnOS computes rigid optical flow and compares it against the optical flow estimated from the FlowNet, yielding pixels satisfying the rigid-scene assumption. Then, we encourage geometrical consistency between the two estimated flows within rigid regions, from which we derive a rigid-aware direct visual odometry (RDVO) module. We also propose rigid and occlusion-aware flow-consistency losses for the learning of UnOS. We evaluated our results on the popular KITTI dataset over 4 related tasks, \ie stereo depth, optical flow, visual odometry and motion segmentation.

Optical flow estimation is a research core of computer vision. In recent years, optical flow estimation methods based on convolutional neural networks (CNNs) have achieved great success. However, most of the existing CNN-based methods are incapable of modeling long-distance dependencies successfully due to the limited receptive fields of convolutions. This may lead to poor performance of optical flow estimation in regions of large displacements and local ambiguities. Furthermore, the problem of edge-blurring remains an open challenge for CNN-based optical flow methods because the general interpolation operation tends to amplify the optical flow errors during the upsampling process. To deal with the abovementioned problems, this paper proposes a novel optical flow estimation method based on local-global modeling and visual similarity guidance. First, an efficient and simple self-attention module is adopted to improve the local-global modeling ability of the network and to extract the more representative features, which decreases the number of optical flow errors caused by large displacements. Second, based on the assumption that the visual features of the objects are more similar, the motion is more similar, and a visual similarity-guided optical flow upsampling network is constructed to guide the upsampling process. By transforming the visual similarity of features into motion similarity, the proposed upsampling scheme improves the accuracy of optical flow estimation in regions of motion boundaries. Finally, we run the proposed method on MPI-Sintel and KITTI test datasets to conduct a comprehensive comparison with some state-of-the-art methods. The experimental results indicate that the proposed method achieves top performance among the comparable methods and, in particular, gains significant developments in regions of large displacements and motion boundaries.

<p indent=0mm>Combining the deep learning model to compute end-to-end optical flow is a hot topic in current computer vision field. The optical flow estimation methods based on deep learning are summarized and reviewed. Firstly, the origin and concept of optical flow is introduced. Secondly, the optical flow datasets and evaluation metrics are summarized. Most importantly, classical methods are introduced and the deep optical flow estimation methods are reviewed in three aspects, including supervised deep optical flow estimation methods, unsupervised deep optical flow estimation methods and the performance of these methods. The analysis shows designing compact and generalized deep optical flow model is the future research direction. On this basis, the joint learning of optical flow estimation and specific video analysis tasks are introduced. It is pointed out that the design of task-driven deep optical flow network is a valuable research direction in practice application. Finally, the problems and challenges of deep optical flow estimation are summarized and the future work of this field is prospected.

This paper reports an optical based method for quantification of cardiac motion in MRI images. The cardiac motion is quantified in a Short-Axis (SAX) slice located at the mid-cavity of the left ventricle. In this slice, the left ventricle wall is segmented for extracting the endocardium, the epicardium and the mid‑wall. The velocity field for these contours is available after performing the optical flow estimation for the given slice. Post-processing of this motion field enables estimation of the radial displacement. The core of this cardiac motion quantification method is a sparse based algorithm for optical flow estimation. This algorithm is presented and compared with several classical optical flow estimation algorithms. The comparison is performed using several video sequences available from the Middlebury benchmark where the ground truth optical flow is known. The algorithms with better performance are also tested using a 4‑ D cardiac Magnetic Resonance Image (MRI) sequence. Results show that he sparse algorithm estimates an optical flow field that represents the motion of contraction during the systole interval. Moreover, results about radial displacement estimation on real MRI sequences for a normal subject and a patient with hypertrophy show that the proposed quantification method could be useful for quantification of left ventricle motion.

In general, discretization in the motion vector domain yields an intractable number of labels. In this paper, we propose an approach that can reduce general optical flow to the constrained matching problem by pre-estimating a 2-D disparity labeling map of the desired discrete motion vector function. One of the goals of the proposed paper is estimating coarse distribution of motion vectors and then utilizing this distribution as global constraints for discrete optical flow estimation. This pre-estimation is done with a simple frame-to-frame correlation technique also known as the digital symmetric-phase-only-filter (SPOF). We discover a strong correlation between the output of the SPOF and the motion vector distribution of the related optical flow. A two step matching paradigm for optical flow estimation is applied: pixel accuracy (integer flow) and subpixel accuracy estimation. The matching problem is solved by global optimization. Experiments on the Middlebury optical flow datasets confirm our intuitive assumptions about strong correlation between motion vector distribution of optical flow and maximal peaks of SPOF outputs. The overall performance of the proposed method is promising and achieves state-of-the-art results on the Middlebury benchmark.

Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too much on local clues and ignore the integrity of objects, resulting in fragmented motion estimation. Through theoretical analysis, we find the pre-trained large vision models are helpful in optical flow estimation, and we notice that the recently famous Segment Anything Model (SAM) demonstrates a strong ability to segment complete objects, which is suitable for solving the fragmentation problem. We thus propose a solution to embed the frozen SAM image encoder into FlowFormer to enhance object perception. To address the challenge of in-depth utilizing SAM in non-segmentation tasks like optical flow estimation, we propose an Optical Flow Task-Specific Adaption scheme, including a Context Fusion Module to fuse the SAM encoder with the optical flow context encoder, and a Context Adaption Module to adapt the SAM features for optical flow task with Learned Task-Specific Embedding. Our proposed SAMFlow model reaches 0.86/2.10 clean/final EPE and 3.55/12.32 EPE/F1-all on Sintel and KITTI-15 training set, surpassing Flowformer by 8.5%/9.9% and 13.2%/16.3%. Furthermore, our model achieves state-of-the-art performance on the Sintel and KITTI-15 benchmarks, ranking #1 among all two-frame methods on Sintel clean pass.

Event cameras are novel bio-inspired sensors that offer advantages over traditional cameras (low latency, high dynamic range, low power, etc.). Optical flow estimation methods that work on packets of events trade off speed for accuracy, while event-by-event (incremental) methods have strong assumptions and have not been tested on common benchmarks that quantify progress in the field. Towards applications on resource-constrained devices, it is important to develop optical flow algorithms that are fast, light-weight and accurate. This work leverages insights from neuroscience, and proposes a novel optical flow estimation scheme based on triplet matching. The experiments on publicly available benchmarks demonstrate its capability to handle complex scenes with comparable results as prior packet-based algorithms. In addition, the proposed method achieves the fastest execution time ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\gt$</tex-math></inline-formula> 10 kHz) on standard CPUs as it requires only three events in estimation. We hope that our research opens the door to real-time, incremental motion estimation methods and applications in real-world scenarios.

Temporal segmentation of a video sequence into different shots is fundamental to a number of video retrieval and analysis applications. Motion estimation has been wildly used in many applications of video processing, since it provides the most essential information for an image sequence. In this paper, we explore the possibility to exploit motion and illumination estimation in a video sequence to detect various types of shot changes. Optical flow is the motion vector computed at each pixel in an image sequence from intensity variation. Traditionally, optical flow computational algorithms were derived from the brightness constancy assumption. In this paper, we employ a generalized optical flow constraint that includes an illumination parameter to model local illumination changes. An iterative optical flow and illumination estimation algorithm is developed in this paper to refine the generalized optical flow constraints step by step, thus leading to a very accurate estimation of the optical flow and illumination parameters. Two robust measures are defined from the mean and standard deviation of the estimated intensity compensation values for all the blocks in the same image. Either of these two measures corresponds significantly to various types of shot changes. We show the usefulness of these two measures through experiments.

In recent years, biking has been popular and getting more and more attention in many country. However, because of its poor protectability, the accident will often result in serious consequences. This study combines a bicycle, a camera and a handheld computing device, and applies a vision-based approaching-vehicle detection algorithm to remind driver to ”watch” his/her back. For the approaching-vehicle detection algorithm, firstly, the optical flow estimation is applied to track a small number of feature points. These tracked points are utilized to estimate the homography transform between two consecutive frames by using RANdom SAmple Consensus algorithm (RANSAC). Therefore, two consecutive frames can be aligned and moving foreground can thus be extracted by performing image subtraction. Once again, feature points within the moving foreground are tracked and weighted by the camera geometry of vanishing point. The weighting procedure eliminates false alarms and effectively detects the vehicles which are approaching the camera. The system has been successfully implemented on the iPhone platform, and validated the feasibility of the system and the effectiveness of the algorithm in the general urban scenario.

Optical flow estimation is a fundamental problem of computer vision and has many applications in the fields of robot learning and autonomous driving. This paper reveals novel geometric principles of optical flow based on the insight and detailed definition of non-occlusion. Then, two novel loss functions are proposed for the unsupervised learning of optical flow based on the geometric principles of non-occlusion. Specifically, after the occlusion part of the images are masked, the flowing process of pixel coordinate points is carefully considered and geometric constraints are conducted based on the geometric principles of optical flow. First, the optical flow vectors of neighboring pixel coordinate points in the first frame will not intersect during the pixel displacement to the second frame. Secondly, when the cluster containing adjacent four pixel coordinate points in the first frame moves to the second frame, no other pixel coordinate points will flow into the quadrilateral formed by them. According to the two geometrical constraints, the optical flow non-intersection loss and the optical flow non-blocking loss in the non-occlusion regions are proposed. Two loss functions punish the irregular and inexact optical flows in the non-occlusion regions. The experiments on datasets demonstrated that the proposed unsupervised losses of optical flow based on the geometric principles in non-occlusion regions make the estimated optical flow more refined in detail, and improve the performance of unsupervised learning of optical flow. In addition, the experiments training on synthetic data and evaluating on real data show that the generalization ability of optical flow network is improved by our proposed unsupervised approach. Our codes are open sourced at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/IRMVLab/NccFlow</uri> .

Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have made good attempts, the domain shift between the synthetic and real adverse weather images would deteriorate their performance. To alleviate this issue, our start point is to unsupervisedly transfer the knowledge from source clean domain to target degraded domain. Our key insight is that adverse weather does not change the intrinsic optical flow of the scene, but causes a significant difference for the warp error between clean and degraded images. In this work, we propose the first unsupervised framework for adverse weather optical flow via hierarchical motion-boundary adaptation. Specifically, we first employ image translation to construct the transformation relationship between clean and degraded domains. In motion adaptation, we utilize the flow consistency knowledge to align the cross-domain optical flows into a motion-invariance common space, where the optical flow from clean weather is used as the guidance-knowledge to obtain a preliminary optical flow for adverse weather. Furthermore, we leverage the warp error inconsistency which measures the motion misalignment of the boundary between the clean and degraded domains, and propose a joint intra- and inter-scene boundary contrastive adaptation to refine the motion boundary. The hierarchical motion and boundary adaptation jointly promotes optical flow in a unified framework. Extensive quantitative and qualitative experiments have been performed to verify the superiority of the proposed method.

Confidence measures are crucial to the interpretation of any optical flow measurement. Even though numerous methods for estimating optical flow have been proposed over the last three decades, a sound, universal, and statistically motivated confidence measure for optical flow measurements is still missing. We aim at filling this gap with this contribution, where such a confidence measure is derived, using statistical test theory and measurable statistics of flow fields from the regarded domain. The new confidence measure is computed from merely the results of the optical flow estimator and hence can be applied to any optical flow estimation method, covering the range from local parametric to global variational approaches. Experimental results using state-of-the-art optical flow estimators and various test sequences demonstrate the superiority of the proposed technique compared to existing ’confidence’ measures.KeywordsOptical FlowConfidence MeasureEndpoint ErrorIntrinsic DimensionalityOptical Flow EstimatorThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.