Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this assumption is violated which leads to an ambiguity between the ego-motion of the camera and the motion of the objects. To solve this problem, we present a self-supervised learning framework for 3D object motion field estimation from monocular videos. Our contributions are two-fold. First, we propose a two-stage projection pipeline to explicitly disentangle the camera ego-motion and the object motions with dynamics attention module, called DAM. Specifically, we design an integrated motion model that estimates the motion of the camera and object in the first and second warping stages, respectively, controlled by the attention module through a shared motion encoder. Second, we propose an object motion field estimation through contrastive sample consensus, called CSAC, taking advantage of weak semantic prior (bounding box from an object detector) and geometric constraints (each object respects the rigid body motion model). Experiments on KITTI, Cityscapes, and Waymo Open Dataset demonstrate the relevance of our approach and show that our method outperforms state-of-the-art algorithms for the tasks of self-supervised monocular depth estimation, object motion segmentation, monocular scene flow estimation, and visual odometry.
Recent advances in object segmentation have demonstrated that deep neural networks excel at object segmentation for specific classes in color and depth images. However, their performance is dictated by the number of classes and objects used for training, thereby hindering generalization to never seen objects or zero-shot samples. To exacerbate the problem further, object segmentation using image frames rely on recognition and pattern matching cues. Instead, we utilize the 'active' nature of a robot and their ability to 'interact' with the environment to induce additional geometric constraints for segmenting zero-shot samples. In this paper, we present the first framework to segment unknown objects in a cluttered scene by repeatedly 'nudging' at the objects and moving them to obtain additional motion cues at every step using only a monochrome monocular camera. We call our framework NudgeSeg. These motion cues are used to refine the segmentation masks. We successfully test our approach to segment novel objects in various cluttered scenes and provide an extensive study with image and motion segmentation methods. We show an impressive average detection rate of over 86% on zero-shot objects.
The extension of conventional clustering to hypergraph clustering, which involves higher order similarities instead of pairwise similarities, is increasingly gaining attention in computer vision. This is due to the fact that many grouping problems require an affinity measure that must involve a subset of data of size more than two, i.e., a hyperedge. Almost all previous works, however, have considered the smallest possible hyperedge size, due to a lack of study into the potential benefits of large hyperedges and effective algorithms to generate them. In this paper, we show that large hyperedges are better from both theoretical and empirical standpoints. We then propose a novel guided sampling strategy for large hyperedges, based on the concept of random cluster models. Our method can generate pure large hyperedges that significantly improve grouping accuracy without exponential increases in sampling costs. In the important applications of face clustering and motion segmentation, our method demonstrates substantially better accuracy and efficiency.
Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage prior knowledge from a source domain to improve clustering performance on a target domain, and currently they represent the state of the art in HMS. Bucking this trend, in this paper, we propose a novel unsupervised model that learns a representation of the data and digs clustering information from the data itself. Our model is reminiscent of temporal subspace clustering, but presents two critical differences. First, we learn an auxiliary data matrix that can deviate from the initial data, hence confer more degrees of freedom to the coding matrix. Second, we introduce a regularization term for this auxiliary data matrix that preserves the local geometrical structure present in the high-dimensional space. The proposed model is efficiently optimized by using an original Alternating Direction Method of Multipliers (ADMM) formulation allowing to learn jointly the auxiliary data representation, a nonnegative dictionary and a coding matrix. Experimental results on four benchmark datasets for HMS demonstrate that our approach achieves significantly better clustering performance then state-of-the-art methods, including both unsupervised and more recent semi-supervised transfer learning approaches.
Detection of moving objects is a very important task in autonomous driving systems. After the perception phase, motion planning is typically performed in Bird's Eye View (BEV) space. This would require projection of objects detected on the image plane to top view BEV plane. Such a projection is prone to errors due to lack of depth information and noisy mapping in far away areas. CNNs can leverage the global context in the scene to project better. In this work, we explore end-to-end Moving Object Detection (MOD) on the BEV map directly using monocular images as input. To the best of our knowledge, such a dataset does not exist and we create an extended KITTI-raw dataset consisting of 12.9k images with annotations of moving object masks in BEV space for five classes. The dataset is intended to be used for class agnostic motion cue based object detection and classes are provided as meta-data for better tuning. We design and implement a two-stream RGB and optical flow fusion architecture which outputs motion segmentation directly in BEV space. We compare it with inverse perspective mapping of state-of-the-art motion segmentation predictions on the image plane. We observe a significant improvement of 13% in mIoU using the simple baseline implementation. This demonstrates the ability to directly learn motion segmentation output in BEV space. Qualitative results of our baseline and the dataset annotations can be found in https://sites.google.com/view/bev-modnet.
This article explores subspace clustering algorithms using CUR decompositions, and examines the effect of various hyperparameters in these algorithms on clustering performance on two real-world benchmark datasets, the Hopkins155 motion segmentation dataset and the Yale face dataset. Extensive experiments are done for a variety of sampling methods and oversampling parameters for these datasets, and some guidelines for parameter choices are given for practical applications.
Our goal in this work is to generate realistic videos given just one initial frame as input. Existing unsupervised approaches to this task do not consider the fact that a video typically shows a 3D environment, and that this should remain coherent from frame to frame even as the camera and objects move. We address this by developing a model that first estimates the latent 3D structure of the scene, including the segmentation of any moving objects. It then predicts future frames by simulating the object and camera dynamics, and rendering the resulting views. Importantly, it is trained end-to-end using only the unsupervised objective of predicting future frames, without any 3D information nor segmentation annotations. Experiments on two challenging datasets of natural videos show that our model can estimate 3D structure and motion segmentation from a single frame, and hence generate plausible and varied predictions.
Spectral-based subspace clustering methods have proved successful in many challenging applications such as gene sequencing, image recognition, and motion segmentation. In this work, we first propose a novel spectral-based subspace clustering algorithm that seeks to represent each point as a sparse convex combination of a few nearby points. We then extend the algorithm to constrained clustering and active learning settings. Our motivation for developing such a framework stems from the fact that typically either a small amount of labelled data is available in advance; or it is possible to label some points at a cost. The latter scenario is typically encountered in the process of validating a cluster assignment. Extensive experiments on simulated and real data sets show that the proposed approach is effective and competitive with state-of-the-art methods.
The minimum cost lifted multicut approach has proven practically good performance in a wide range of applications such as image decomposition, mesh segmentation, multiple object tracking, and motion segmentation. It addresses such problems in a graph-based model, where real-valued costs are assigned to the edges between entities such that the minimum cut decomposes the graph into an optimal number of segments. Driven by a probabilistic formulation of minimum cost multicuts, we provide a measure for the uncertainties of the decisions made during the optimization. We argue that access to such uncertainties is crucial for many practical applications and conduct an evaluation by means of sparsifications on three different, widely used datasets in the context of image decomposition (BSDS-500) and motion segmentation (DAVIS2016 and FBMS59) in terms of variation of information (VI) and Rand index (RI).
Spiking Neural Networks (SNN) are the so-called third generation of neural networks which attempt to more closely match the functioning of the biological brain. They inherently encode temporal data, allowing for training with less energy usage and can be extremely energy efficient when coded on neuromorphic hardware. In addition, they are well suited for tasks involving event-based sensors, which match the event-based nature of the SNN. However, SNNs have not been as effectively applied to real-world, large-scale tasks as standard Artificial Neural Networks (ANNs) due to the algorithmic and training complexity. To exacerbate the situation further, the input representation is unconventional and requires careful analysis and deep understanding. In this paper, we propose \textit{SpikeMS}, the first deep encoder-decoder SNN architecture for the real-world large-scale problem of motion segmentation using the event-based DVS camera as input. To accomplish this, we introduce a novel spatio-temporal loss formulation that includes both spike counts and classification labels in conjunction with the use of new techniques for SNN backpropagation. In addition, we show that \textit{SpikeMS} is capable of \textit{incremental predictions}, or predictions from smaller amounts of test data than it is trained on. This is invaluable for providing outputs even with partial input data for low-latency applications and those requiring fast predictions. We evaluated \textit{SpikeMS} on challenging synthetic and real-world sequences from EV-IMO, EED and MOD datasets and achieving results on a par with a comparable ANN method, but using potentially 50 times less power.
Video prediction is commonly referred to as forecasting future frames of a video sequence provided several past frames thereof. It remains a challenging domain as visual scenes evolve according to complex underlying dynamics, such as the camera's egocentric motion or the distinct motility per individual object viewed. These are mostly hidden from the observer and manifest as often highly non-linear transformations between consecutive video frames. Therefore, video prediction is of interest not only in anticipating visual changes in the real world but has, above all, emerged as an unsupervised learning rule targeting the formation and dynamics of the observed environment. Many of the deep learning-based state-of-the-art models for video prediction utilize some form of recurrent layers like Long Short-Term Memory (LSTMs) or Gated Recurrent Units (GRUs) at the core of their models. Although these models can predict the future frames, they rely entirely on these recurrent structures to simultaneously perform three distinct tasks: extracting transformations, projecting them into the future, and transforming the current frame. In order to completely interpret the formed internal representations, it is crucial to disentangle these tasks. This paper proposes a fully differentiable building block that can perform all of those tasks separately while maintaining interpretability. We derive the relevant theoretical foundations and showcase results on synthetic as well as real data. We demonstrate that our method is readily extended to perform motion segmentation and account for the scene's composition, and learns to produce reliable predictions in an entirely interpretable manner by only observing unlabeled video data.
People often use physical intuition when manipulating articulated objects, irrespective of object semantics. Motivated by this observation, we identify an important embodied task where an agent must play with objects to recover their parts. To this end, we introduce Act the Part (AtP) to learn how to interact with articulated objects to discover and segment their pieces. By coupling action selection and motion segmentation, AtP is able to isolate structures to make perceptual part recovery possible without semantic labels. Our experiments show AtP learns efficient strategies for part discovery, can generalize to unseen categories, and is capable of conditional reasoning for the task. Although trained in simulation, we show convincing transfer to real world data with no fine-tuning.
We introduce a visual motion segmentation method employing spherical geometry for fisheye cameras and automoated driving. Three commonly used geometric constraints in pin-hole imagery (the positive height, positive depth and epipolar constraints) are reformulated to spherical coordinates, making them invariant to specific camera configurations as long as the camera calibration is known. A fourth constraint, known as the anti-parallel constraint, is added to resolve motion-parallax ambiguity, to support the detection of moving objects undergoing parallel or near-parallel motion with respect to the host vehicle. A final constraint constraint is described, known as the spherical three-view constraint, is described though not employed in our proposed algorithm. Results are presented and analyzed that demonstrate that the proposal is an effective motion segmentation approach for direct employment on fisheye imagery.
Animals have evolved highly functional visual systems to understand motion, assisting perception even under complex environments. In this paper, we work towards developing a computer vision system able to segment objects by exploiting motion cues, i.e. motion segmentation. We make the following contributions: First, we introduce a simple variant of the Transformer to segment optical flow frames into primary objects and the background. Second, we train the architecture in a self-supervised manner, i.e. without using any manual annotations. Third, we analyze several critical components of our method and conduct thorough ablation studies to validate their necessity. Fourth, we evaluate the proposed architecture on public benchmarks (DAVIS2016, SegTrackv2, and FBMS59). Despite using only optical flow as input, our approach achieves superior or comparable results to previous state-of-the-art self-supervised methods, while being an order of magnitude faster. We additionally evaluate on a challenging camouflage dataset (MoCA), significantly outperforming the other self-supervised approaches, and comparing favourably to the top supervised approach, highlighting the importance of motion cues, and the potential bias towards visual appearance in existing video segmentation models.
Semantic segmentation approaches are typically trained on large-scale data with a closed finite set of known classes without considering unknown objects. In certain safety-critical robotics applications, especially autonomous driving, it is important to segment all objects, including those unknown at training time. We formalize the task of video class agnostic segmentation from monocular video sequences in autonomous driving to account for unknown objects. Video class agnostic segmentation can be formulated as an open-set or a motion segmentation problem. We discuss both formulations and provide datasets and benchmark different baseline approaches for both tracks. In the motion-segmentation track we benchmark real-time joint panoptic and motion instance segmentation, and evaluate the effect of ego-flow suppression. In the open-set segmentation track we evaluate baseline methods that combine appearance, and geometry to learn prototypes per semantic class. We then compare it to a model that uses an auxiliary contrastive loss to improve the discrimination between known and unknown objects. Datasets and models are publicly released at https://msiam.github.io/vca/.
This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the proposed approach uses 3D convolutions as a key technology to factor in, spatio-temporal features in cohesive video frames. This is done by capturing temporal information in features with a low and also with a high level of abstraction. The lean network architecture with about 21k trainable parameters is mainly based on a pre-trained VGG-16 network. The MOSNET uses a new feature map fusion technique, which enables the network to focus on the appropriate level of abstraction, resolution, and the appropriate size of the receptive field regarding the input. Furthermore, the end-to-end deep learning based approach can be extended by feature based image alignment as a pre-processing step, which brings a gain in performance for some scenes. Evaluating the end-to-end deep learning based MOSNET network in a scene independent manner leads to an overall F-measure of 0.803 on the CDNet2014 dataset. A small temporal window of five input frames, without the need of any initialization is used to obtain this result. Therefore the network is able to perform well on scenes captured with non-static cameras where the image content changes significantly during the scene. In order to get robust results in scenes captured with a moving camera, feature based image alignment can implemented as pre-processing step. The MOSNET combined with pre-processing leads to an F-measure of 0.685 when cross-evaluating with a relabeled LASIESTA dataset, which underpins the capability generalise of the MOSNET.
Surround View fisheye cameras are commonly deployed in automated driving for 360\deg{} near-field sensing around the vehicle. This work presents a multi-task visual perception network on unrectified fisheye images to enable the vehicle to sense its surrounding environment. It consists of six primary tasks necessary for an autonomous driving system: depth estimation, visual odometry, semantic segmentation, motion segmentation, object detection, and lens soiling detection. We demonstrate that the jointly trained model performs better than the respective single task versions. Our multi-task model has a shared encoder providing a significant computational advantage and has synergized decoders where tasks support each other. We propose a novel camera geometry based adaptation mechanism to encode the fisheye distortion model both at training and inference. This was crucial to enable training on the WoodScape dataset, comprised of data from different parts of the world collected by 12 different cameras mounted on three different cars with different intrinsics and viewpoints. Given that bounding boxes is not a good representation for distorted fisheye images, we also extend object detection to use a polygon with non-uniformly sampled vertices. We additionally evaluate our model on standard automotive datasets, namely KITTI and Cityscapes. We obtain the state-of-the-art results on KITTI for depth estimation and pose estimation tasks and competitive performance on the other tasks. We perform extensive ablation studies on various architecture choices and task weighting methodologies. A short video at https://youtu.be/xbSjZ5OfPes provides qualitative results.
In this paper we introduce a Transformer-based approach to video object segmentation (VOS). To address compounding error and scalability issues of prior work, we propose a scalable, end-to-end method for VOS called Sparse Spatiotemporal Transformers (SST). SST extracts per-pixel representations for each object in a video using sparse attention over spatiotemporal features. Our attention-based formulation for VOS allows a model to learn to attend over a history of multiple frames and provides suitable inductive bias for performing correspondence-like computations necessary for solving motion segmentation. We demonstrate the effectiveness of attention-based over recurrent networks in the spatiotemporal domain. Our method achieves competitive results on YouTube-VOS and DAVIS 2017 with improved scalability and robustness to occlusions compared with the state of the art. Code is available at https://github.com/dukebw/SSTVOS.
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing different spatial arrangements of bodies or body parts; and (ii) obtaining robust motion-based rigid body segmentation applicable to novel object categories. We propose an approach to address these issues that incorporates spectral synchronization into an iterative deep declarative network, so as to simultaneously recover consistent correspondences as well as motion segmentation. At the same time, by explicitly disentangling the correspondence and motion segmentation estimation modules, we achieve strong generalizability across different object categories. Our extensive evaluations demonstrate that our method is effective on various datasets ranging from rigid parts in articulated objects to individually moving objects in a 3D scene, be it single-view or full point clouds.
Appearance-based detectors achieve remarkable performance on common scenes, but tend to fail for scenarios lack of training data. Geometric motion segmentation algorithms, however, generalize to novel scenes, but have yet to achieve comparable performance to appearance-based ones, due to noisy motion estimations and degenerate motion configurations. To combine the best of both worlds, we propose a modular network, whose architecture is motivated by a geometric analysis of what independent object motions can be recovered from an egomotion field. It takes two consecutive frames as input and predicts segmentation masks for the background and multiple rigidly moving objects, which are then parameterized by 3D rigid transformations. Our method achieves state-of-the-art performance for rigid motion segmentation on KITTI and Sintel. The inferred rigid motions lead to a significant improvement for depth and scene flow estimation. At the time of submission, our method ranked 1st on KITTI scene flow leaderboard, out-performing the best published method (scene flow error: 4.89% vs 6.31%).