Successful aquaculture systems can reduce the pressure and help secure the most diverse and productive Red Sea coral reef ecosystem to maintain a healthy and functional ecosystem within a sustainable blue economy. Interestingly, recirculating aquaculture systems are currently emerging in fish farm production practices. On the other hand, monitoring and detecting fish behaviors provide essential information on fish welfare and contribute to an intelligent production in global aquaculture. This work proposes an efficient approach to analyze the spatial distribution status and motion patterns of juvenile clownfish \textit{(Amphiprion bicinctus)} maintained in aquaria at three stocking densities (1, 5, and 10 individuals/aquarium). The estimated displacement is crucial in assessing the dispersion and velocity to express the clownfish's spatial distribution and movement behavior in a recirculating aquaculture system. Indeed, we aim to compute the velocity, magnitude, and turning angle using an optical flow method to assist aquaculturists in efficiently monitoring and identifying fish behavior. We test the system design on a database containing two days of video streams of juvenile clownfish maintained in aquaria. The proposed displacement estimation reveals good performance in measuring clownfish's motion and dispersion characteristics leading to assessing the potential signs of stress behaviors. We demonstrate the effectiveness of the proposed technique for quantifying variation in clownfish activity levels between recordings taken in the morning and afternoon at different stocking densities. It provides practical baseline support for online predicting and monitoring feeding behavior in ornamental fish aquaculture.
Fast neuromorphic event-based vision sensors (Dynamic Vision Sensor, DVS) can be combined with slower conventional frame-based sensors to enable higher-quality inter-frame interpolation than traditional methods relying on fixed motion approximations using e.g. optical flow. In this work we present a new, advanced event simulator that can produce realistic scenes recorded by a camera rig with an arbitrary number of sensors located at fixed offsets. It includes a new configurable frame-based image sensor model with realistic image quality reduction effects, and an extended DVS model with more accurate characteristics. We use our simulator to train a novel reconstruction model designed for end-to-end reconstruction of high-fps video. Unlike previously published methods, our method does not require the frame and DVS cameras to have the same optics, positions, or camera resolutions. It is also not limited to objects a fixed distance from the sensor. We show that data generated by our simulator can be used to train our new model, leading to reconstructed images on public datasets of equivalent or better quality than the state of the art. We also show our sensor generalizing to data recorded by real sensors.
Event cameras capture changes of illumination in the observed scene rather than accumulating light to create images. Thus, they allow for applications under high-speed motion and complex lighting conditions, where traditional framebased sensors show their limits with blur and over- or underexposed pixels. Thanks to these unique properties, they represent nowadays an highly attractive sensor for ITS-related applications. Event-based optical flow (EBOF) has been studied following the rise in popularity of these neuromorphic cameras. The recent arrival of high-definition neuromorphic sensors, however, challenges the existing approaches, because of the increased resolution of the events pixel array and a much higher throughput. As an answer to these points, we propose an optimized framework for computing optical flow in real-time with both low- and high-resolution event cameras. We formulate a novel dense representation for the sparse events flow, in the form of the "inverse exponential distance surface". It serves as an interim frame, designed for the use of proven, state-of-the-art frame-based optical flow computation methods. We evaluate our approach on both low- and high-resolution driving sequences, and show that it often achieves better results than the current state of the art, while also reaching higher frame rates, 250Hz at 346 x 260 pixels and 77Hz at 1280 x 720 pixels.
Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, the complex physical interaction and its non-trivial visual appearance.Yet, hair is a critical component for believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is com-posed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural rendering. 2) To have a reliable control signal, we present a novel way of tracking hair on the strand level. To keep the computational effort manageable, we use guide hairs and classic techniques to expand those into a dense hood of hair. 3) To better enforce temporal consistency and generalization ability of our model, we further optimize the 3D scene flow of our representation with multi-view optical flow, using volumetric ray marching. Our method can not only create realistic renders of recorded multi-view sequences, but also create renderings for new hair configurations by providing new control signals. We compare our method with existing work on viewpoint synthesis and drivable animation and achieve state-of-the-art results. Please check out our project website at https://ziyanw1.github.io/hvh/.
Event-based vision sensors produce asynchronous event streams with high temporal resolution based on changes in the visual scene. The properties of these sensors allow for accurate and fast calculation of optical flow as events are generated. Existing solutions for calculating optical flow from event data either fail to capture the true direction of motion due to the aperture problem, do not use the high temporal resolution of the sensor, or are too computationally expensive to be run in real time on embedded platforms. In this research, we first present a faster version of our previous algorithm, ARMS (Aperture Robust Multi-Scale flow). The new optimized software version (fARMS) significantly improves throughput on a traditional CPU. Further, we present hARMS, a hardware realization of the fARMS algorithm allowing for real-time computation of true flow on low-power, embedded platforms. The proposed hARMS architecture targets hybrid system-on-chip devices and was designed to maximize configurability and throughput. The hardware architecture and fARMS algorithm were developed with asynchronous neuromorphic processing in mind, abandoning the common use of an event frame and instead operating using only a small history of relevant events, allowing latency to scale independently of the sensor resolution. This change in processing paradigm improved the estimation of flow directions by up to 73% compared to the existing method and yielded a demonstrated hARMS throughput of up to 1.21 Mevent/s on the benchmark configuration selected. This throughput enables real-time performance and makes it the fastest known realization of aperture-robust, event-based optical flow to date.
Event cameras are novel bio-inspired sensors that measure per-pixel brightness differences asynchronously. Recovering brightness from events is appealing since the reconstructed images inherit the high dynamic range (HDR) and high-speed properties of events; hence they can be used in many robotic vision applications and to generate slow-motion HDR videos. However, state-of-the-art methods tackle this problem by training an event-to-image Recurrent Neural Network (RNN), which lacks explainability and is difficult to tune. In this work we show, for the first time, how tackling the combined problem of motion and brightness estimation leads us to formulate event-based image reconstruction as a linear inverse problem that can be solved without training an image reconstruction RNN. Instead, classical and learning-based regularizers are used to solve the problem and remove artifacts from the reconstructed images. The experiments show that the proposed approach generates images with visual quality on par with state-of-the-art methods despite only using data from a short time interval. State-of-the-art results are achieved using an image denoising Convolutional Neural Network (CNN) as the regularization function. The proposed regularized formulation and solvers have a unifying character because they can be applied also to reconstruct brightness from the second derivative. Additionally, the formulation is attractive because it can be naturally combined with super-resolution, motion-segmentation and color demosaicing. Code is available at https://github.com/tub-rip/event_based_image_rec_inverse_problem
Image stitching aims at stitching the images taken from different viewpoints into an image with a wider field of view. Existing methods warp the target image to the reference image using the estimated warp function, and a homography is one of the most commonly used warping functions. However, when images have large parallax due to non-planar scenes and translational motion of a camera, the homography cannot fully describe the mapping between two images. Existing approaches based on global or local homography estimation are not free from this problem and suffer from undesired artifacts due to parallax. In this paper, instead of relying on the homography-based warp, we propose a novel deep image stitching framework exploiting the pixel-wise warp field to handle the large-parallax problem. The proposed deep image stitching framework consists of two modules: Pixel-wise Warping Module (PWM) and Stitched Image Generating Module (SIGMo). PWM employs an optical flow estimation model to obtain pixel-wise warp of the whole image, and relocates the pixels of the target image with the obtained warp field. SIGMo blends the warped target image and the reference image while eliminating unwanted artifacts such as misalignments, seams, and holes that harm the plausibility of the stitched result. For training and evaluating the proposed framework, we build a large-scale dataset that includes image pairs with corresponding pixel-wise ground truth warp and sample stitched result images. We show that the results of the proposed framework are qualitatively superior to those of the conventional methods, especially when the images have large parallax. The code and the proposed dataset will be publicly available soon.
LiDAR sensors are widely used in autonomous driving due to the reliable 3D spatial information. However, the data of LiDAR is sparse and the frequency of LiDAR is lower than that of cameras. To generate denser point clouds spatially and temporally, we propose the first future pseudo-LiDAR frame prediction network. Given the consecutive sparse depth maps and RGB images, we first predict a future dense depth map based on dynamic motion information coarsely. To eliminate the errors of optical flow estimation, an inter-frame aggregation module is proposed to fuse the warped depth maps with adaptive weights. Then, we refine the predicted dense depth map using static contextual information. The future pseudo-LiDAR frame can be obtained by converting the predicted dense depth map into corresponding 3D point clouds. Experimental results show that our method outperforms the existing solutions on the popular KITTI benchmark.
Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the computational burden and also avoids the negative impact of background noise. However, unlike pixel-based methods, which could directly exploit explicit motion features such as optical flow, pose-based methods suffer from the lack of alternative dynamic representation. In this paper, a novel Motion Embedder (ME) is proposed to provide a pose motion representation from the probability perspective. Furthermore, a novel task-specific Spatial-Temporal Transformer (STT) is deployed for self-supervised pose sequence reconstruction. These two modules are then integrated into a unified framework for pose regularity learning, which is referred to as Motion Prior Regularity Learner (MoPRL). MoPRL achieves the state-of-the-art performance by an average improvement of 4.7% AUC on several challenging datasets. Extensive experiments validate the versatility of each proposed module.
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution and require significantly less power and memory than traditional frame-based cameras. These characteristics make them a perfect fit to several real-world applications such as egocentric action recognition on wearable devices, where fast camera motion and limited power challenge traditional vision sensors. However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications. In this paper, we show that event data is a very valuable modality for egocentric action recognition. To do so, we introduce N-EPIC-Kitchens, the first event-based camera extension of the large-scale EPIC-Kitchens dataset. In this context, we propose two strategies: (i) directly processing event-camera data with traditional video-processing architectures (E$^2$(GO)) and (ii) using event-data to distill optical flow information (E$^2$(GO)MO). On our proposed benchmark, we show that event data provides a comparable performance to RGB and optical flow, yet without any additional flow computation at deploy time, and an improved performance of up to 4% with respect to RGB only information.
We propose a method to interactively control the animation of fluid elements in still images to generate cinemagraphs. Specifically, we focus on the animation of fluid elements like water, smoke, fire, which have the properties of repeating textures and continuous fluid motion. Taking inspiration from prior works, we represent the motion of such fluid elements in the image in the form of a constant 2D optical flow map. To this end, we allow the user to provide any number of arrow directions and their associated speeds along with a mask of the regions the user wants to animate. The user-provided input arrow directions, their corresponding speed values, and the mask are then converted into a dense flow map representing a constant optical flow map (FD). We observe that FD, obtained using simple exponential operations can closely approximate the plausible motion of elements in the image. We further refine computed dense optical flow map FD using a generative-adversarial network (GAN) to obtain a more realistic flow map. We devise a novel UNet based architecture to autoregressively generate future frames using the refined optical flow map by forward-warping the input image features at different resolutions. We conduct extensive experiments on a publicly available dataset and show that our method is superior to the baselines in terms of qualitative and quantitative metrics. In addition, we show the qualitative animations of the objects in directions that did not exist in the training set and provide a way to synthesize videos that otherwise would not exist in the real world.
Video frame interpolation, which aims to synthesize non-exist intermediate frames in a video sequence, is an important research topic in computer vision. Existing video frame interpolation methods have achieved remarkable results under specific assumptions, such as instant or known exposure time. However, in complicated real-world situations, the temporal priors of videos, i.e. frames per second (FPS) and frame exposure time, may vary from different camera sensors. When test videos are taken under different exposure settings from training ones, the interpolated frames will suffer significant misalignment problems. In this work, we solve the video frame interpolation problem in a general situation, where input frames can be acquired under uncertain exposure (and interval) time. Unlike previous methods that can only be applied to a specific temporal prior, we derive a general curvilinear motion trajectory formula from four consecutive sharp frames or two consecutive blurry frames without temporal priors. Moreover, utilizing constraints within adjacent motion trajectories, we devise a novel optical flow refinement strategy for better interpolation results. Finally, experiments demonstrate that one well-trained model is enough for synthesizing high-quality slow-motion videos under complicated real-world situations. Codes are available on https://github.com/yjzhang96/UTI-VFI.
Cost-based image patch matching is at the core of various techniques in computer vision, photogrammetry and remote sensing. When the subpixel disparity between the reference patch in the source and target images is required, either the cost function or the target image have to be interpolated. While cost-based interpolation is the easiest to implement, multiple works have shown that image based interpolation can increase the accuracy of the subpixel matching, but usually at the cost of expensive search procedures. This, however, is problematic, especially for very computation intensive applications such as stereo matching or optical flow computation. In this paper, we show that closed form formulae for subpixel disparity computation for the case of one dimensional matching, e.g., in the case of rectified stereo images where the search space is of one dimension, exists when using the standard NCC, SSD and SAD cost functions. We then demonstrate how to generalize the proposed formulae to the case of high dimensional search spaces, which is required for unrectified stereo matching and optical flow extraction. We also compare our results with traditional cost volume interpolation formulae as well as with state-of-the-art cost-based refinement methods, and show that the proposed formulae bring a small improvement over the state-of-the-art cost-based methods in the case of one dimensional search spaces, and a significant improvement when the search space is two dimensional.
Video data is often repetitive; for example, the contents of adjacent frames are usually strongly correlated. Such redundancy occurs at multiple levels of complexity, from low-level pixel values to textures and high-level semantics. We propose Event Neural Networks (EvNets), which leverage this redundancy to achieve considerable computation savings during video inference. A defining characteristic of EvNets is that each neuron has state variables that provide it with long-term memory, which allows low-cost, high-accuracy inference even in the presence of significant camera motion. We show that it is possible to transform a wide range of neural networks into EvNets without re-training. We demonstrate our method on state-of-the-art architectures for both high- and low-level visual processing, including pose recognition, object detection, optical flow, and image enhancement. We observe roughly an order-of-magnitude reduction in computational costs compared to conventional networks, with minimal reductions in model accuracy.
We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement. Supervision is provided by a novel loss which measures the distance between this predicted flow subspace and an observed optical flow. This provides a new approach to learning scene representation tasks, such as monocular depth prediction or instance segmentation, in an unsupervised fashion using in-the-wild input videos without requiring camera poses, intrinsics, or an explicit multi-view stereo step. We evaluate our method in multiple settings, including an indoor depth prediction task where it achieves comparable performance to recent methods trained with more supervision.
This paper proposes a novel particle image velocimetry (PIV) technique to generate an instantaneous two-dimensional velocity field for sediment-laden fluid based on the optical flow algorithm of ultrasound imaging. In this paper, an ultrasonic PIV (UPIV) system is constructed by integrating a medical ultrasound instrument and an ultrasonic particle image velocimetry algorithm. The medical ultrasound instrument with a phased sensor array is used to acquire acoustic echo signals and generate two-dimensional underwater ultrasound images. Based on the optical flow field, the instantaneous velocity of the particles in water corresponding to the pixels in the ultrasonic particle images is derived from the grayscale change between adjacent images under the L-K local constraint, and finally, the two-dimensional flow field is obtained. Through multiple sets of experiments, the proposed algorithm is verified. The experimental results are compared with those of the conventional cross-correlation algorithms. The results show that the L-K optical flow method can not only obtain the underwater velocity field accurately but also has the advantages of good smoothness and extensive suitability, especially for the flow field measurement in sediment-laden fluid than conventional algorithms.
Advection-diffusion equations describe a large family of natural transport processes, e.g., fluid flow, heat transfer, and wind transport. They are also used for optical flow and perfusion imaging computations. We develop a machine learning model, D^2-SONATA, built upon a stochastic advection-diffusion equation, which predicts the velocity and diffusion fields that drive 2D/3D image time-series of transport. In particular, our proposed model incorporates a model of transport atypicality, which isolates abnormal differences between expected normal transport behavior and the observed transport. In a medical context such a normal-abnormal decomposition can be used, for example, to quantify pathologies. Specifically, our model identifies the advection and diffusion contributions from the transport time-series and simultaneously predicts an anomaly value field to provide a decomposition into normal and abnormal advection and diffusion behavior. To achieve improved estimation performance for the velocity and diffusion-tensor fields underlying the advection-diffusion process and for the estimation of the anomaly fields, we create a 2D/3D anomaly-encoded advection-diffusion simulator, which allows for supervised learning. We further apply our model on a brain perfusion dataset from ischemic stroke patients via transfer learning. Extensive comparisons demonstrate that our model successfully distinguishes stroke lesions (abnormal) from normal brain regions, while reconstructing the underlying velocity and diffusion tensor fields.
Existing deep learning based unsupervised video object segmentation methods still rely on ground-truth segmentation masks to train. Unsupervised in this context only means that no annotated frames are used during inference. As obtaining ground-truth segmentation masks for real image scenes is a laborious task, we envision a simple framework for dominant moving object segmentation that neither requires annotated data to train nor relies on saliency priors or pre-trained optical flow maps. Inspired by a layered image representation, we introduce a technique to group pixel regions according to their affine parametric motion. This enables our network to learn segmentation of the dominant foreground object using only RGB image pairs as input for both training and inference. We establish a baseline for this novel task using a new MovingCars dataset and show competitive performance against recent methods that require annotated masks to train.
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements. To alleviate this, the state-of-the-art framework RAFT gradually improves its prediction quality by using a large number of iterative refinements, achieving remarkable performance but introducing linearly increasing inference time. To enable both high accuracy and efficiency, we completely revamp the dominant flow regression pipeline by reformulating optical flow as a global matching problem, which identifies the correspondences by directly comparing feature similarities. Specifically, we propose a GMFlow framework, which consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. We further introduce a refinement step that reuses GMFlow at higher feature resolution for residual flow prediction. Our new framework outperforms 31-refinements RAFT on the challenging Sintel benchmark, while using only one refinement and running faster, suggesting a new paradigm for accurate and efficient optical flow estimation. Code is available at https://github.com/haofeixu/gmflow.
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Recent work on simple 2D and 3D datasets has shown that models with object-centric inductive biases can learn to segment and represent meaningful objects from the statistical structure of the data alone without the need for any supervision. However, such fully-unsupervised methods still fail to scale to diverse realistic data, despite the use of increasingly complex inductive biases such as priors for the size of objects or the 3D geometry of the scene. In this paper, we instead take a weakly-supervised approach and focus on how 1) using the temporal dynamics of video data in the form of optical flow and 2) conditioning the model on simple object location cues can be used to enable segmenting and tracking objects in significantly more realistic synthetic data. We introduce a sequential extension to Slot Attention which we train to predict optical flow for realistic looking synthetic scenes and show that conditioning the initial state of this model on a small set of hints, such as center of mass of objects in the first frame, is sufficient to significantly improve instance segmentation. These benefits generalize beyond the training distribution to novel objects, novel backgrounds, and to longer video sequences. We also find that such initial-state-conditioning can be used during inference as a flexible interface to query the model for specific objects or parts of objects, which could pave the way for a range of weakly-supervised approaches and allow more effective interaction with trained models.