An official website of the United States government
Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to obtain. Self-supervised keypoint discovery is a promising strategy for estimating 3D poses without annotations. However, current keypoint discovery approaches commonly process single 2D views and do not operate in the 3D space. We propose a new method to perform self-supervised keypoint discovery in 3D from multi-view videos of behaving agents, without any keypoint or bounding box supervision in 2D or 3D. Our method uses an encoder-decoder architecture with a 3D volumetric heatmap, trained to reconstruct spatiotemporal differences across multiple views, in addition to joint length constraints on a learned 3D skeleton of the subject. In this way, we discover keypoints without requiring manual supervision in videos of humans and rats, demonstrating the potential of 3D keypoint discovery for studying behavior.
more »
« less
Traffic4D: Single View Longitudinal 4D Reconstruction of Repetitious Activity using Self-Supervised Experts
Reconstructing 4D vehicular activity (3D space and time) from cameras is useful for autonomous vehicles, commuters and local authorities to plan for smarter and safer cities. Traffic is inherently repetitious over long periods, yet current deep learning-based 3D reconstruction methods have not considered such repetitions and have difficulty generalizing to new intersection-installed cameras. We present a novel approach exploiting longitudinal (long-term) repetitious motion as self-supervision to reconstruct 3D vehicular activity from a video captured by a single fixed camera. Starting from off-the-shelf 2D keypoint detections, our algorithm optimizes 3D vehicle shapes and poses, and then clusters their trajectories in 3D space. The 2D keypoints and trajectory clusters accumulated over long-term are later used to improve the 2D and 3D keypoints via self-supervision without any human annotation. Our method improves reconstruction accuracy over state of the art on scenes with a significant visual difference from the keypoint detector’s training data, and has many applications including velocity estimation, anomaly detection and vehicle counting. We demonstrate results on traffic videos captured at multiple city intersections, collected using our smartphones, YouTube, and other public datasets.
more »
« less
- PAR ID:
- 10292805
- Date Published:
- Journal Name:
- IEEE Intelligent Vehicles Symposium
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper presents a visual servoing method for controlling a robot in the configuration space by purely using its natural features. We first created a data collection pipeline that uses camera intrinsics, extrinsics, and forward kinematics to generate 2D projections of a robot's joint locations (keypoints) in image space. Using this pipeline, we are able to collect large sets of real-robot data, which we use to train realtime keypoint detectors. The inferred keypoints from the trained model are used as control features in an adaptive visual servoing scheme that estimates, in runtime, the Jacobian relating the changes of the keypoints and joint velocities. We compared the 2D configuration control performance of this method to the skeleton-based visual servoing method (the only other algorithm for purely vision-based configuration space visual servoing), and demonstrated that the keypoints provide more robust and less noisy features, which result in better transient response. We also demonstrate the first vision-based 3D configuration space control results in the literature, and discuss its limitations. Our data collection pipeline is available at https://github.com/JaniC-WPI/KPDataGenerator.git which can be utilized to collect image datasets and train realtime keypoint detectors for various robots and environments.more » « less
-
Despite achieving impressive improvement in accuracy, most existing monocular 3D human mesh reconstruction methods require large-scale 2D/3D ground-truths for supervision, which limits their applications on unlabeled in-the-wild data that is ubiquitous. To alleviate the reliance on 2D/3D ground-truths, we present a self-supervised 3D human pose and shape reconstruction framework that relies only on self-consistency between intermediate representations of images and projected 2D predictions. Specifically, we extract 2D joints and depth maps from monocular images as proxy inputs, which provides complementary clues to infer accurate 3D human meshes. Furthermore, to reduce the impacts from noisy and ambiguous inputs while better concentrate on the high-quality information, we design an uncertainty-aware module to automatically learn the reliability of the inputs at body-joint level based on the consistency between 2D joints and depth map. Experiments on benchmark datasets show that our approach outperforms other state-of-the-art methods at similar supervision levels.more » « less
-
IEEE (Ed.)Over past few years, unmanned aircraft vehicles (UAVs) have been becoming more and more popular for various purposes such as surveillance, automated industry, robotics, vehicle guidance, traffic monitoring and control system. It is very important to have multiple methods of UAVs controlling to fit in UAVs usages. The goal of this work was to develop a new technique to control an UAV by using different hand gestures. To achieve this, a hand keypoint detection algorithm was used to detect 21 keypoints in the hand. Then this keypoints were used as the input to an intelligent system based on Convolutional Neural Networks (CNN) that was able to classify the hand gestures. To capture the hand gestures, the video camera of the UAV was used. A database containing 2400 hand images was created and used to train the CNN. The database contained 8 different hand gestures that were selected to send specific motion commands to the UAV. The accuracy of the CNN to classify the hand gestures was 93%. To test the capabilities of our intelligent control system, a small UAV, the DJI Ryze Tello drone, was used. The experimental results demonstrated that the DJI Tello drone was able to be successfully controlled by hand gestures in real time.more » « less
-
Real-world robotics applications demand object pose estimation methods that work reliably across a variety of scenarios. Modern learning-based approaches require large labeled datasets and tend to perform poorly outside the training domain. Our first contribution is to develop a robust corrector module that corrects pose estimates using depth information, thus enabling existing methods to better generalize to new test domains; the corrector operates on semantic keypoints (but is also applicable to other pose estimators) and is fully differentiable. Our second contribution is an ensemble self-training approach that simultaneously trains multiple pose estimators in a self-supervised manner. Our ensemble self-training architecture uses the robust corrector to refine the output of each pose estimator; then, it evaluates the quality of the outputs using observable correctness certificates; finally, it uses the observably correct outputs for further training, without requiring external supervision. As an additional contribution, we propose small improvements to a regression-based keypoint detection architecture, to enhance its robustness to outliers; these improvements include a robust pooling scheme and a robust centroid computation. Experiments on the YCBV and TLESS datasets show the proposed ensemble self-training outperforms fully supervised baselines while not requiring 3D annotations on real data.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
