In many applications of advanced robotic manipulation, six degrees of freedom (6DoF) object pose estimates are continuously required. In this work, we develop a multi-modality tracker that fuses information from visual appearance and geometry to estimate object poses. The algorithm extends our previous method ICG, which uses geometry, to additionally consider surface appearance. In general, object surfaces contain local characteristics from text, graphics, and patterns, as well as global differences from distinct materials and colors. To incorporate this visual information, two modalities are developed. For local characteristics, keypoint features are used to minimize distances between points from keyframes and the current image. For global differences, a novel region approach is developed that considers multiple regions on the object surface. In addition, it allows the modeling of external geometries. Experiments on the YCB-Video and OPT datasets demonstrate that our approach ICG+ performs best on both datasets, outperforming both conventional and deep learning-based methods. At the same time, the algorithm is highly efficient and runs at more than 300 Hz. The source code of our tracker is publicly available.
There exist no publicly available annotated underwater multi-object tracking (MOT) datasets captured in turbid environments. To remedy this we propose the BrackishMOT dataset with focus on tracking schools of small fish, which is a notoriously difficult MOT task. BrackishMOT consists of 98 sequences captured in the wild. Alongside the novel dataset, we present baseline results by training a state-of-the-art tracker. Additionally, we propose a framework for creating synthetic sequences in order to expand the dataset. The framework consists of animated fish models and realistic underwater environments. We analyse the effects of including synthetic data during training and show that a combination of real and synthetic underwater training data can enhance tracking performance. Links to code and data can be found at https://www.vap.aau.dk/brackishmot
Annotating object ground truth in videos is vital for several downstream tasks in robot perception and machine learning, such as for evaluating the performance of an object tracker or training an image-based object detector. The accuracy of the annotated instances of the moving objects on every image frame in a video is crucially important. Achieving that through manual annotations is not only very time consuming and labor intensive, but is also prone to high error rate. State-of-the-art annotation methods depend on manually initializing the object bounding boxes only in the first frame and then use classical tracking methods, e.g., adaboost, or kernelized correlation filters, to keep track of those bounding boxes. These can quickly drift, thereby requiring tedious manual supervision. In this paper, we propose a new annotation method which leverages a combination of a learning-based detector (SSD) and a learning-based tracker (RE$^3$). Through this, we significantly reduce annotation drifts, and, consequently, the required manual supervision. We validate our approach through annotation experiments using our proposed annotation method and existing baselines on a set of drone video frames. Source code and detailed information on how to run the annotation program can be found at https://github.com/robot-perception-group/smarter-labelme
Diffusion models have enabled high-quality, conditional image editing capabilities. We propose to expand their arsenal, and demonstrate that off-the-shelf diffusion models can be used for a wide range of cross-domain compositing tasks. Among numerous others, these include image blending, object immersion, texture-replacement and even CG2Real translation or stylization. We employ a localized, iterative refinement scheme which infuses the injected objects with contextual information derived from the background scene, and enables control over the degree and types of changes the object may undergo. We conduct a range of qualitative and quantitative comparisons to prior work, and exhibit that our method produces higher quality and realistic results without requiring any annotations or training. Finally, we demonstrate how our method may be used for data augmentation of downstream tasks.
Cross-view multi-object tracking aims to link objects between frames and camera views with substantial overlaps. Although cross-view multi-object tracking has received increased attention in recent years, existing datasets still have several issues, including 1) missing real-world scenarios, 2) lacking diverse scenes, 3) owning a limited number of tracks, 4) comprising only static cameras, and 5) lacking standard benchmarks, which hinder the investigation and comparison of cross-view tracking methods. To solve the aforementioned issues, we introduce DIVOTrack: a new cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians in realistic and non-experimental environments. Our DIVOTrack has fifteen distinct scenarios and 953 cross-view tracks, surpassing all cross-view multi-object tracking datasets currently available. Furthermore, we provide a novel baseline cross-view tracking method with a unified joint detection and cross-view tracking framework named CrossMOT, which learns object detection, single-view association, and cross-view matching with an all-in-one embedding model. Finally, we present a summary of current methodologies and a set of standard benchmarks with our DIVOTrack to provide a fair comparison and conduct a comprehensive analysis of current approaches and our proposed CrossMOT. The dataset and code are available at https://github.com/shengyuhao/DIVOTrack.
Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quality or flexible pseudo labels, leading to serious inconsistency problems in SSOD. In this paper, we propose the Efficient Teacher framework for scalable and effective one-stage anchor-based SSOD training, consisting of Dense Detector, Pseudo Label Assigner, and Epoch Adaptor. Dense Detector is a baseline model that extends RetinaNet with dense sampling techniques inspired by YOLOv5. The Efficient Teacher framework introduces a novel pseudo label assignment mechanism, named Pseudo Label Assigner, which makes more refined use of pseudo labels from Dense Detector. Epoch Adaptor is a method that enables a stable and efficient end-to-end semi-supervised training schedule for Dense Detector. The Pseudo Label Assigner prevents the occurrence of bias caused by a large number of low-quality pseudo labels that may interfere with the Dense Detector during the student-teacher mutual learning mechanism, and the Epoch Adaptor utilizes domain and distribution adaptation to allow Dense Detector to learn globally distributed consistent features, making the training independent of the proportion of labeled data. Our experiments show that the Efficient Teacher framework achieves state-of-the-art results on VOC, COCO-standard, and COCO-additional using fewer FLOPs than previous methods. To the best of our knowledge, this is the first attempt to apply Semi-Supervised Object Detection to YOLOv5.Code is available: https://github.com/AlibabaResearch/efficientteacher
This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.
Digital twin is a problem of augmenting real objects with their digital counterparts. It can underpin a wide range of applications in augmented reality (AR), autonomy, and UI/UX. A critical component in a good digital-twin system is real-time, accurate 3D object tracking. Most existing works solve 3D object tracking through the lens of robotic grasping, employ older generations of depth sensors, and measure performance metrics that may not apply to other digital-twin applications such as in AR. In this work, we create a novel RGB-D dataset, called Digital Twin Tracking Dataset (DTTD), to enable further research of the problem and extend potential solutions towards longer ranges and mm localization accuracy. To reduce point cloud noise from the input source, we select the latest Microsoft Azure Kinect as the state-of-the-art time-of-flight (ToF) camera. In total, 103 scenes of 10 common off-the-shelf objects with rich textures are recorded, with each frame annotated with a per-pixel semantic segmentation and ground-truth object poses provided by a commercial motion capturing system. Through extensive experiments with model-level and dataset-level analysis, we demonstrate that DTTD can help researchers develop future object tracking methods and analyze new challenges. The dataset, data generation, annotation, and model evaluation pipeline are made publicly available as open source code at: https://github.com/augcog/DTTDv1.
Autonomous driving needs to rely on high-quality 3D object detection to ensure safe navigation in the world. Uncertainty estimation is an effective tool to provide statistically accurate predictions, while the associated detection uncertainty can be used to implement a more safe navigation protocol or include the user in the loop. In this paper, we propose a Variational Neural Network-based TANet 3D object detector to generate 3D object detections with uncertainty and introduce these detections to an uncertainty-aware AB3DMOT tracker. This is done by applying a linear transformation to the estimated uncertainty matrix, which is subsequently used as a measurement noise for the adopted Kalman filter. We implement two ways to estimate output uncertainty, i.e., internally, by computing the variance of the CNN outputs and then propagating the uncertainty through the post-processing, and externally, by associating the final predictions of different samples and computing the covariance of each predicted box. In experiments, we show that the external uncertainty estimation leads to better results, outperforming both internal uncertainty estimation and classical tracking approaches. Furthermore, we propose a method to initialize the Variational 3D object detector with a pretrained TANet model, which leads to the best performing models.
Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for detection tasks. One is the serious imbalance between foreground and background features, another one is that small object lacks enough feature representation. To solve the above issues, we propose a new distillation method named dual relation knowledge distillation (DRKD), including pixel-wise relation distillation and instance-wise relation distillation. The pixel-wise relation distillation embeds pixel-wise features in the graph space and applies graph convolution to capture the global pixel relation. By distilling the global pixel relation, the student detector can learn the relation between foreground and background features, and avoid the difficulty of distilling features directly for the feature imbalance issue. Besides, we find that instance-wise relation supplements valuable knowledge beyond independent features for small objects. Thus, the instance-wise relation distillation is designed, which calculates the similarity of different instances to obtain a relation matrix. More importantly, a relation filter module is designed to highlight valuable instance relations. The proposed dual relation knowledge distillation is general and can be easily applied for both one-stage and two-stage detectors. Our method achieves state-of-the-art performance, which improves Faster R-CNN based on ResNet50 from 38.4% to 41.6% mAP and improves RetinaNet based on ResNet50 from 37.4% to 40.3% mAP on COCO 2017.
Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks. However, little attention has been paid to this topic in Optical Remote Sensing Images (O-RSIs). To this end, we focus on this research, i.e., PAs on object detection in O-RSIs, and propose a more Threatening PA without the scarification of the visual quality, dubbed TPA. Specifically, to address the problem of inconsistency between local and global landscapes in existing patch selection schemes, we propose leveraging the First-Order Difference (FOD) of the objective function before and after masking to select the sub-patches to be attacked. Further, considering the problem of gradient inundation when applying existing coordinate-based loss to PAs directly, we design an IoU-based objective function specific for PAs, dubbed Bounding box Drifting Loss (BDL), which pushes the detected bounding boxes far from the initial ones until there are no intersections between them. Finally, on two widely used benchmarks, i.e., DIOR and DOTA, comprehensive evaluations of our TPA with four typical detectors (Faster R-CNN, FCOS, RetinaNet, and YOLO-v4) witness its remarkable effectiveness. To the best of our knowledge, this is the first attempt to study the PAs on object detection in O-RSIs, and we hope this work can get our readers interested in studying this topic.
Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorporate equivariance to per-object pose transformations into the attention and generation mechanism of Slot Attention by translating, scaling, and rotating position encodings. These changes result in little computational overhead, are easy to implement, and can result in large gains in terms of data efficiency and overall improvements to object discovery. We evaluate our method on a wide range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVRTex, Objects Room and MultiShapeNet, and show promising improvements on the challenging real-world Waymo Open dataset.
This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning for Tracking" (PF-Track). Specifically, our method adapts the "tracking by attention" framework and represents tracked instances coherently over time with object queries. To explicitly use historical cues, our "Past Reasoning" module learns to refine the tracks and enhance the object features by cross-attending to queries from previous frames and other objects. The "Future Reasoning" module digests historical information and predicts robust future trajectories. In the case of long-term occlusions, our method maintains the object positions and enables re-association by integrating motion predictions. On the nuScenes dataset, our method improves AMOTA by a large margin and remarkably reduces ID-Switches by 90% compared to prior approaches, which is an order of magnitude less. The code and models are made available at https://github.com/TRI-ML/PF-Track.
When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., a fully self-supervised approach. In our setting, an agent initially learns to explore the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we learn the exploration policy Look Around to mine hard samples, and we devise a novel mechanism called Disagreement Reconciliation for producing refined pseudo-labels from the consensus among observations. We implement a unified benchmark of the current state-of-the-art and compare our approach with pre-existing exploration policies and perception mechanisms. Our method is shown to outperform existing approaches, improving the object detector by 6.2% in a simulated scenario, a 3.59% advancement over other state-of-the-art methods, and by 9.97% in the real robotic test without relying on ground-truth. Code for the proposed approach and baselines are available at https://iit-pavis.github.io/Look_Around_And_Learn/.
Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human motor capacity and objects' physical property thus benefiting tasks such as action anticipation and robot imitation learning. However, the definition of affordance in existing datasets often: 1) mix up affordance with object functionality; 2) confuse affordance with goal-related action; and 3) ignore human motor capacity. This paper proposes an efficient annotation scheme to address these issues by combining goal-irrelevant motor actions and grasp types as affordance labels and introducing the concept of mechanical action to represent the action possibilities between two objects. We provide new annotations by applying this scheme to the EPIC-KITCHENS dataset and test our annotation with tasks such as affordance recognition, hand-object interaction hotspots prediction, and cross-domain evaluation of affordance. The results show that models trained with our annotation can distinguish affordance from other concepts, predict fine-grained interaction possibilities on objects, and generalize through different domains.
Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. However, since the target objects in these existing datasets are usually relatively salient, dominant, and isolated, VOS under complex scenes has rarely been studied. To revisit VOS and make it more applicable in the real world, we collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex environments. MOSE contains 2,149 video clips and 5,200 objects from 36 categories, with 431,725 high-quality object segmentation masks. The most notable feature of MOSE dataset is complex scenes with crowded and occluded objects. The target objects in the videos are commonly occluded by others and disappear in some frames. To analyze the proposed MOSE dataset, we benchmark 18 existing VOS methods under 4 different settings on the proposed MOSE dataset and conduct comprehensive comparisons. The experiments show that current VOS algorithms cannot well perceive objects in complex scenes. For example, under the semi-supervised VOS setting, the highest J&F by existing state-of-the-art VOS methods is only 59.4% on MOSE, much lower than their ~90% J&F performance on DAVIS. The results reveal that although excellent performance has been achieved on existing benchmarks, there are unresolved challenges under complex scenes and more efforts are desired to explore these challenges in the future. The proposed MOSE dataset has been released at https://henghuiding.github.io/MOSE.
We present vMAP, an object-level dense SLAM system using neural field representations. Each object is represented by a small MLP, enabling efficient, watertight object modelling without the need for 3D priors. As an RGB-D camera browses a scene with no prior information, vMAP detects object instances on-the-fly, and dynamically adds them to its map. Specifically, thanks to the power of vectorised training, vMAP can optimise as many as 50 individual objects in a single scene, with an extremely efficient training speed of 5Hz map update. We experimentally demonstrate significantly improved scene-level and object-level reconstruction quality compared to prior neural field SLAM systems. Project page: https://kxhit.github.io/vMAP.
Prompt tuning with large-scale pretrained vision-language models empowers open-vocabulary predictions trained on limited base categories, e.g., object classification and detection. In this paper, we propose compositional prompt tuning with motion cues: an extended prompt tuning paradigm for compositional predictions of video data. In particular, we present Relation Prompt (RePro) for Open-vocabulary Video Visual Relation Detection (Open-VidVRD), where conventional prompt tuning is easily biased to certain subject-object combinations and motion patterns. To this end, RePro addresses the two technical challenges of Open-VidVRD: 1) the prompt tokens should respect the two different semantic roles of subject and object, and 2) the tuning should account for the diverse spatio-temporal motion patterns of the subject-object compositions. Without bells and whistles, our RePro achieves a new state-of-the-art performance on two VidVRD benchmarks of not only the base training object and predicate categories, but also the unseen ones. Extensive ablations also demonstrate the effectiveness of the proposed compositional and multi-mode design of prompts. Code is available at https://github.com/Dawn-LX/OpenVoc-VidVRD.
In this paper, we address the problem of estimating the in-hand 6D pose of an object in contact with multiple vision-based tactile sensors. We reason on the possible spatial configurations of the sensors along the object surface. Specifically, we filter contact hypotheses using geometric reasoning and a Convolutional Neural Network (CNN), trained on simulated object-agnostic images, to promote those that better comply with the actual tactile images from the sensors. We use the selected sensors configurations to optimize over the space of 6D poses using a Gradient Descent-based approach. We finally rank the obtained poses by penalizing those that are in collision with the sensors. We carry out experiments in simulation using the DIGIT vision-based sensor with several objects, from the standard YCB model set. The results demonstrate that our approach estimates object poses that are compatible with actual object-sensor contacts in $87.5\%$ of cases while reaching an average positional error in the order of $2$ centimeters. Our analysis also includes qualitative results of experiments with a real DIGIT sensor.
As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this issue, we propose a meta-learning framework with two novel feature aggregation schemes. More precisely, we first present a Class-Agnostic Aggregation (CAA) method, where the query and support features can be aggregated regardless of their categories. The interactions between different classes encourage class-agnostic representations and reduce confusion between base and novel classes. Based on the CAA, we then propose a Variational Feature Aggregation (VFA) method, which encodes support examples into class-level support features for robust feature aggregation. We use a variational autoencoder to estimate class distributions and sample variational features from distributions that are more robust to the variance of support examples. Besides, we decouple classification and regression tasks so that VFA is performed on the classification branch without affecting object localization. Extensive experiments on PASCAL VOC and COCO demonstrate that our method significantly outperforms a strong baseline (up to 16\%) and previous state-of-the-art methods (4\% in average). Code will be available at: \url{https://github.com/csuhan/VFA}