In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and pose estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate poses by assigning keypoints to person instances. On the COCO keypoints dataset, our pose estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: https://github.com/mkocabas/pose-residual-network
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.
Convolutional neural nets (convnets) trained from massive labeled datasets have substantially improved the state-of-the-art in image classification and object detection. However, visual understanding requires establishing correspondence on a finer level than object category. Given their large pooling regions and training from whole-image labels, it is not clear that convnets derive their success from an accurate correspondence model which could be used for precise localization. In this paper, we study the effectiveness of convnet activation features for tasks requiring correspondence. We present evidence that convnet features localize at a much finer scale than their receptive field sizes, that they can be used to perform intraclass alignment as well as conventional hand-engineered features, and that they outperform conventional features in keypoint prediction on objects from PASCAL VOC 2011.
A number of computer vision tasks exploit a succinct representation of the visual content in the form of sets of local features. Given an input image, feature extraction algorithms identify a set of keypoints and assign to each of them a description vector, based on the characteristics of the visual content surrounding the interest point. Several tasks might require local features to be extracted from a video sequence, on a frame-by-frame basis. Although temporal downsampling has been proven to be an effective solution for mobile augmented reality and visual search, high temporal resolution is a key requirement for time-critical applications such as object tracking, event recognition, pedestrian detection, surveillance. In recent years, more and more computationally efficient visual feature detectors and decriptors have been proposed. Nonetheless, such approaches are tailored to still images. In this paper we propose a fast keypoint detection algorithm for video sequences, that exploits the temporal coherence of the sequence of keypoints. According to the proposed method, each frame is preprocessed so as to identify the parts of the input frame for which keypoint detection and description need to be performed. Our experiments show that it is possible to achieve a reduction in computational time of up to 40%, without significantly affecting the task accuracy.
We characterize the problem of pose estimation for rigid objects in terms of determining viewpoint to explain coarse pose and keypoint prediction to capture the finer details. We address both these tasks in two different settings - the constrained setting with known bounding boxes and the more challenging detection setting where the aim is to simultaneously detect and correctly estimate pose of objects. We present Convolutional Neural Network based architectures for these and demonstrate that leveraging viewpoint estimates can substantially improve local appearance based keypoint predictions. In addition to achieving significant improvements over state-of-the-art in the above tasks, we analyze the error modes and effect of object characteristics on performance to guide future efforts towards this goal.
The most popular image matching algorithm SIFT, introduced by D. Lowe a decade ago, has proven to be sufficiently scale invariant to be used in numerous applications. In practice, however, scale invariance may be weakened by various sources of error inherent to the SIFT implementation affecting the stability and accuracy of keypoint detection. The density of the sampling of the Gaussian scale-space and the level of blur in the input image are two of these sources. This article presents a numerical analysis of their impact on the extracted keypoints stability. Such an analysis has both methodological and practical implications, on how to compare feature detectors and on how to improve SIFT. We show that even with a significantly oversampled scale-space numerical errors prevent from achieving perfect stability. Usual strategies to filter out unstable detections are shown to be inefficient. We also prove that the effect of the error in the assumption on the initial blur is asymmetric and that the method is strongly degraded in presence of aliasing or without a correct assumption on the camera blur.
In many mobile visual analysis applications, compressed video is transmitted over a communication network and analyzed by a server. Typical processing steps performed at the server include keypoint detection, descriptor calculation, and feature matching. Video compression has been shown to have an adverse effect on feature-matching performance. The negative impact of compression can be reduced by using the keypoints extracted from the uncompressed video to calculate descriptors from the compressed video. Based on this observation, we propose to provide these keypoints to the server as side information and to extract only the descriptors from the compressed video. First, we introduce four different frame types for keypoint encoding to address different types of changes in video content. These frame types represent a new scene, the same scene, a slowly changing scene, or a rapidly moving scene and are determined by comparing features between successive video frames. Then, we propose Intra, Skip and Inter modes of encoding the keypoints for different frame types. For example, keypoints for new scenes are encoded using the Intra mode, and keypoints for unchanged scenes are skipped. As a result, the bitrate of the side information related to keypoint encoding is significantly reduced. Finally, we present pairwise matching and image retrieval experiments conducted to evaluate the performance of the proposed approach using the Stanford mobile augmented reality dataset and 720p format videos. The results show that the proposed approach offers significantly improved feature matching and image retrieval performance at a given bitrate.
Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which lack enough flexibility to meet the requirements for various applications. In this paper, we propose a new method on the basis of deep learning by formulating the 3D keypoint detection as a regression problem using deep neural network (DNN) with sparse autoencoder (SAE) as our regression model. Both local information and global information of a 3D mesh model in multi-scale space are fully utilized to detect whether a vertex is a keypoint or not. SAE can effectively extract the internal structure of these two kinds of information and formulate high-level features for them, which is beneficial to the regression model. Three SAEs are used to formulate the hidden layers of the DNN and then a logistic regression layer is trained to process the high-level features produced in the third SAE. Numerical experiments show that the proposed DNN based 3D keypoint detection algorithm outperforms current five state-of-the-art methods for various 3D mesh models.
Despite of the recent success of neural networks for human pose estimation, current approaches are limited to pose estimation of a single person and cannot handle humans in groups or crowds. In this work, we propose a method that estimates the poses of multiple persons in an image in which a person can be occluded by another person or might be truncated. To this end, we consider multi-person pose estimation as a joint-to-person association problem. We construct a fully connected graph from a set of detected joint candidates in an image and resolve the joint-to-person association and outlier detection using integer linear programming. Since solving joint-to-person association jointly for all persons in an image is an NP-hard problem and even approximations are expensive, we solve the problem locally for each person. On the challenging MPII Human Pose Dataset for multiple persons, our approach achieves the accuracy of a state-of-the-art method, but it is 6,000 to 19,000 times faster.
We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn semantic parts and gives new understanding of the internal representations of CNNs. Our technique is based on the hypothesis that semantic parts are represented by populations of neurons rather than by single filters. We propose a clustering technique to extract part representations, which we call Visual Concepts. We show that visual concepts are semantically coherent in that they represent semantic parts, and visually coherent in that corresponding image patches appear very similar. Also, visual concepts provide full spatial coverage of the parts of an object, rather than a few sparse parts as is typically found in keypoint annotations. Furthermore, We treat single visual concept as part detector and evaluate it for keypoint detection using the PASCAL3D+ dataset and for part detection using our newly annotated ImageNetPart dataset. The experiments demonstrate that visual concepts can be used to detect parts. We also show that some visual concepts respond to several semantic parts, provided these parts are visually similar. Thus visual concepts have the essential properties: semantic meaning and detection capability. Note that our ImageNetPart dataset gives rich part annotations which cover the whole object, making it useful for other part-related applications.
The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de
Copy move forgery detection in digital images has become a very popular research topic in the area of image forensics. Due to the availability of sophisticated image editing tools and ever increasing hardware capabilities, it has become an easy task to manipulate the digital images. Passive forgery detection techniques are more relevant as they can be applied without the prior information about the image in question. Block based techniques are used to detect copy move forgery, but have limitations of large time complexity and sensitivity against affine operations like rotation and scaling. Keypoint based approaches are used to detect forgery in large images where the possibility of significant post processing operations like rotation and scaling is more. A hybrid approach is proposed using different methods for keypoint detection and description. Speeded Up Robust Features (SURF) are used to detect the keypoints in the image and Binary Robust Invariant Scalable Keypoints (BRISK) features are used to describe features at these keypoints. The proposed method has performed better than the existing forgery detection method using SURF significantly in terms of detection speed and is invariant to post processing operations like rotation and scaling. The proposed method is also invariant to other commonly applied post processing operations like adding Gaussian noise and JPEG compression
Keypoint detection is one of the most important pre-processing steps in tasks such as face modeling, recognition and verification. In this paper, we present an iterative method for Keypoint Estimation and Pose prediction of unconstrained faces by Learning Efficient H-CNN Regressors (KEPLER) for addressing the face alignment problem. Recent state of the art methods have shown improvements in face keypoint detection by employing Convolution Neural Networks (CNNs). Although a simple feed forward neural network can learn the mapping between input and output spaces, it cannot learn the inherent structural dependencies. We present a novel architecture called H-CNN (Heatmap-CNN) which captures structured global and local features and thus favors accurate keypoint detecion. HCNN is jointly trained on the visibility, fiducials and 3D-pose of the face. As the iterations proceed, the error decreases making the gradients small and thus requiring efficient training of DCNNs to mitigate this. KEPLER performs global corrections in pose and fiducials for the first four iterations followed by local corrections in the subsequent stage. As a by-product, KEPLER also provides 3D pose (pitch, yaw and roll) of the face accurately. In this paper, we show that without using any 3D information, KEPLER outperforms state of the art methods for alignment on challenging datasets such as AFW and AFLW.
This paper presents a novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. Unlike prior work, we are agnostic to whether the object is textured or textureless, as the convnet learns the optimal representation from the available training image data. Furthermore, the approach can be applied to instance- and class-based pose recovery. Empirically, we show that the proposed approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios with a cluttered background. For class-based object pose estimation, state-of-the-art accuracy is shown on the large-scale PASCAL3D+ dataset.
Recently, Deep Convolution Networks (DCNNs) have been applied to the task of face alignment and have shown potential for learning improved feature representations. Although deeper layers can capture abstract concepts like pose, it is difficult to capture the geometric relationships among the keypoints in DCNNs. In this paper, we propose a novel convolution-deconvolution network for facial keypoint detection. Our model predicts the 2D locations of the keypoints and their individual visibility along with 3D head pose, while exploiting the spatial relationships among different keypoints. Different from existing approaches of modeling these relationships, we propose learnable transform functions which captures the relationships between keypoints at feature level. However, due to extensive variations in pose, not all of these relationships act at once, and hence we propose, a pose-based routing function which implicitly models the active relationships. Both transform functions and the routing function are implemented through convolutions in a multi-task framework. Our approach presents a single-shot keypoint detection method, making it different from many existing cascade regression-based methods. We also show that learning these relationships significantly improve the accuracy of keypoint detections for in-the-wild face images from challenging datasets such as AFW and AFLW.
We present a method for localizing facial keypoints on animals by transferring knowledge gained from human faces. Instead of directly finetuning a network trained to detect keypoints on human faces to animal faces (which is sub-optimal since human and animal faces can look quite different), we propose to first adapt the animal images to the pre-trained human detection network by correcting for the differences in animal and human face shape. We first find the nearest human neighbors for each animal image using an unsupervised shape matching method. We use these matches to train a thin plate spline warping network to warp each animal face to look more human-like. The warping network is then jointly finetuned with a pre-trained human facial keypoint detection network using an animal dataset. We demonstrate state-of-the-art results on both horse and sheep facial keypoint detection, and significant improvement over simple finetuning, especially when training data is scarce. Additionally, we present a new dataset with 3717 images with horse face and facial keypoint annotations.
We propose a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task. It is a simple, yet powerful, top-down approach consisting of two stages. In the first stage, we predict the location and scale of boxes which are likely to contain people; for this we use the Faster RCNN detector. In the second stage, we estimate the keypoints of the person potentially contained in each proposed bounding box. For each keypoint type we predict dense heatmaps and offsets using a fully convolutional ResNet. To combine these outputs we introduce a novel aggregation procedure to obtain highly localized keypoint predictions. We also use a novel form of keypoint-based Non-Maximum-Suppression (NMS), instead of the cruder box-level NMS, and a novel form of keypoint-based confidence score estimation, instead of box-level scoring. Trained on COCO data alone, our final system achieves average precision of 0.649 on the COCO test-dev set and the 0.643 test-standard sets, outperforming the winner of the 2016 COCO keypoints challenge and other recent state-of-art. Further, by using additional in-house labeled data we obtain an even higher average precision of 0.685 on the test-dev set and 0.673 on the test-standard set, more than 5% absolute improvement compared to the previous best performing method on the same dataset.
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.
We present an approach that uses a multi-camera system to train fine-grained detectors for keypoints that are prone to occlusion, such as the joints of a hand. We call this procedure multiview bootstrapping: first, an initial keypoint detector is used to produce noisy labels in multiple views of the hand. The noisy detections are then triangulated in 3D using multiview geometry or marked as outliers. Finally, the reprojected triangulations are used as new labeled training data to improve the detector. We repeat this process, generating more labeled data in each iteration. We derive a result analytically relating the minimum number of views to achieve target true and false positive rates for a given detector. The method is used to train a hand keypoint detector for single images. The resulting keypoint detector runs in realtime on RGB images and has accuracy comparable to methods that use depth sensors. The single view detector, triangulated over multiple views, enables 3D markerless hand motion capture with complex object interactions.
In this paper we propose an approach for articulated tracking of multiple people in unconstrained videos. Our starting point is a model that resembles existing architectures for single-frame pose estimation but is substantially faster. We achieve this in two ways: (1) by simplifying and sparsifying the body-part relationship graph and leveraging recent methods for faster inference, and (2) by offloading a substantial share of computation onto a feed-forward convolutional architecture that is able to detect and associate body joints of the same person even in clutter. We use this model to generate proposals for body joint locations and formulate articulated tracking as spatio-temporal grouping of such proposals. This allows to jointly solve the association problem for all people in the scene by propagating evidence from strong detections through time and enforcing constraints that each proposal can be assigned to one person only. We report results on a public MPII Human Pose benchmark and on a new MPII Video Pose dataset of image sequences with multiple people. We demonstrate that our model achieves state-of-the-art results while using only a fraction of time and is able to leverage temporal information to improve state-of-the-art for crowded scenes.