3D object detection is an essential part of automated driving, and deep neural networks (DNNs) have achieved state-of-the-art performance for this task. However, deep models are notorious for assigning high confidence scores to out-of-distribution (OOD) inputs, that is, inputs that are not drawn from the training distribution. Detecting OOD inputs is challenging and essential for the safe deployment of models. OOD detection has been studied extensively for the classification task, but it has not received enough attention for the object detection task, specifically LiDAR-based 3D object detection. In this paper, we focus on the detection of OOD inputs for LiDAR-based 3D object detection. We formulate what OOD inputs mean for object detection and propose to adapt several OOD detection methods for object detection. We accomplish this by our proposed feature extraction method. To evaluate OOD detection methods, we develop a simple but effective technique of generating OOD objects for a given object detection model. Our evaluation based on the KITTI dataset shows that different OOD detection methods have biases toward detecting specific OOD objects. It emphasizes the importance of combined OOD detection methods and more research in this direction.
Integrating multispectral data in object detection, especially visible and infrared images, has received great attention in recent years. Since visible (RGB) and infrared (IR) images can provide complementary information to handle light variations, the paired images are used in many fields, such as multispectral pedestrian detection, RGB-IR crowd counting and RGB-IR salient object detection. Compared with natural RGB-IR images, we find detection in aerial RGB-IR images suffers from cross-modal weakly misalignment problems, which are manifested in the position, size and angle deviations of the same object. In this paper, we mainly address the challenge of cross-modal weakly misalignment in aerial RGB-IR images. Specifically, we firstly explain and analyze the cause of the weakly misalignment problem. Then, we propose a Translation-Scale-Rotation Alignment (TSRA) module to address the problem by calibrating the feature maps from these two modalities. The module predicts the deviation between two modality objects through an alignment process and utilizes Modality-Selection (MS) strategy to improve the performance of alignment. Finally, a two-stream feature alignment detector (TSFADet) based on the TSRA module is constructed for RGB-IR object detection in aerial images. With comprehensive experiments on the public DroneVehicle datasets, we verify that our method reduces the effect of the cross-modal misalignment and achieve robust detection results.
Visual Search is referred to the task of finding a target object among a set of distracting objects in a visual display. In this paper, based on an independent analysis of the COCO-Search18 dataset, we investigate how the performance of human participants during visual search is affected by different parameters such as the size and eccentricity of the target object. We also study the correlation between the error rate of participants and search performance. Our studies show that a bigger and more eccentric target is found faster with fewer number of fixations. Our code for the graphics are publicly available at https://github.com/ManooshSamiei/COCOSearch18_Analysis.
Teaching a multi-fingered dexterous robot to grasp objects in the real world has been a challenging problem due to its high dimensional state and action space. We propose a robot-learning system that can take a small number of human demonstrations and learn to grasp unseen object poses given partially occluded observations. Our system leverages a small motion capture dataset and generates a large dataset with diverse and successful trajectories for a multi-fingered robot gripper. By adding domain randomization, we show that our dataset provides robust grasping trajectories that can be transferred to a policy learner. We train a dexterous grasping policy that takes the point clouds of the object as input and predicts continuous actions to grasp objects from different initial robot states. We evaluate the effectiveness of our system on a 22-DoF floating Allegro Hand in simulation and a 23-DoF Allegro robot hand with a KUKA arm in real world. The policy learned from our dataset can generalize well on unseen object poses in both simulation and the real world
Road rutting is a severe road distress that can cause premature failure of road incurring early and costly maintenance costs. Research on road damage detection using image processing techniques and deep learning are being actively conducted in the past few years. However, these researches are mostly focused on detection of cracks, potholes, and their variants. Very few research has been done on the detection of road rutting. This paper proposes a novel road rutting dataset comprising of 949 images and provides both object level and pixel level annotations. Object detection models and semantic segmentation models were deployed to detect road rutting on the proposed dataset, and quantitative and qualitative analysis of model predictions were done to evaluate model performance and identify challenges faced in the detection of road rutting using the proposed method. Object detection model YOLOX-s achieves mAP@IoU=0.5 of 61.6% and semantic segmentation model PSPNet (Resnet-50) achieves IoU of 54.69 and accuracy of 72.67, thus providing a benchmark accuracy for similar work in future. The proposed road rutting dataset and the results of our research study will help accelerate the research on detection of road rutting using deep learning.
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that 3D CNNs ignore the redundancy of data and further amplify it in the down-sampling process, which brings a huge amount of extra and unnecessary computational overhead. Inspired by this, we propose a new convolution operator named spatial pruned sparse convolution (SPS-Conv), which includes two variants, spatial pruned submanifold sparse convolution (SPSS-Conv) and spatial pruned regular sparse convolution (SPRS-Conv), both of which are based on the idea of dynamically determining crucial areas for redundancy reduction. We validate that the magnitude can serve as important cues to determine crucial areas which get rid of the extra computations of learning-based methods. The proposed modules can easily be incorporated into existing sparse 3D CNNs without extra architectural modifications. Extensive experiments on the KITTI, Waymo and nuScenes datasets demonstrate that our method can achieve more than 50% reduction in GFLOPs without compromising the performance.
Visual tasks vary a lot in their output formats and concerned contents, therefore it is hard to process them with an identical structure. One main obstacle lies in the high-dimensional outputs in object-level visual tasks. In this paper, we propose an object-centric vision framework, Obj2Seq. Obj2Seq takes objects as basic units, and regards most object-level visual tasks as sequence generation problems of objects. Therefore, these visual tasks can be decoupled into two steps. First recognize objects of given categories, and then generate a sequence for each of these objects. The definition of the output sequences varies for different tasks, and the model is supervised by matching these sequences with ground-truth targets. Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks. When experimenting on MS COCO, Obj2Seq achieves 45.7% AP on object detection, 89.0% AP on multi-label classification and 65.0% AP on human pose estimation. These results demonstrate its potential to be generally applied to different visual tasks. Code has been made available at: https://github.com/CASIA-IVA-Lab/Obj2Seq.
Can a robot manipulate intra-category unseen objects in arbitrary poses with the help of a mere demonstration of grasping pose on a single object instance? In this paper, we try to address this intriguing challenge by using USEEK, an unsupervised SE(3)-equivariant keypoints method that enjoys alignment across instances in a category, to perform generalizable manipulation. USEEK follows a teacher-student structure to decouple the unsupervised keypoint discovery and SE(3)-equivariant keypoint detection. With USEEK in hand, the robot can infer the category-level task-relevant object frames in an efficient and explainable manner, enabling manipulation of any intra-category objects from and to any poses. Through extensive experiments, we demonstrate that the keypoints produced by USEEK possess rich semantics, thus successfully transferring the functional knowledge from the demonstration object to the novel ones. Compared with other object representations for manipulation, USEEK is more adaptive in the face of large intra-category shape variance, more robust with limited demonstrations, and more efficient at inference time.
Many visual phenomena suggest that humans use top-down generative or reconstructive processes to create visual percepts (e.g., imagery, object completion, pareidolia), but little is known about the role reconstruction plays in robust object recognition. We built an iterative encoder-decoder network that generates an object reconstruction and used it as top-down attentional feedback to route the most relevant spatial and feature information to feed-forward object recognition processes. We tested this model using the challenging out-of-distribution digit recognition dataset, MNIST-C, where 15 different types of transformation and corruption are applied to handwritten digit images. Our model showed strong generalization performance against various image perturbations, on average outperforming all other models including feedforward CNNs and adversarially trained networks. Our model is particularly robust to blur, noise, and occlusion corruptions, where shape perception plays an important role. Ablation studies further reveal two complementary roles of spatial and feature-based attention in robust object recognition, with the former largely consistent with spatial masking benefits in the attention literature (the reconstruction serves as a mask) and the latter mainly contributing to the model's inference speed (i.e., number of time steps to reach a certain confidence threshold) by reducing the space of possible object hypotheses. We also observed that the model sometimes hallucinates a non-existing pattern out of noise, leading to highly interpretable human-like errors. Our study shows that modeling reconstruction-based feedback endows AI systems with a powerful attention mechanism, which can help us understand the role of generating perception in human visual processing.
Image-based salient object detection (ISOD) in 360{\deg} scenarios is significant for understanding and applying panoramic information. However, research on 360{\deg} ISOD has not been widely explored due to the lack of large, complex, high-resolution, and well-labeled datasets. Towards this end, we construct a large scale 360{\deg} ISOD dataset with object-level pixel-wise annotation on equirectangular projection (ERP), which contains rich panoramic scenes with not less than 2K resolution and is the largest dataset for 360{\deg} ISOD by far to our best knowledge. By observing the data, we find current methods face three significant challenges in panoramic scenarios: diverse distortion degrees, discontinuous edge effects and changeable object scales. Inspired by humans' observing process, we propose a view-aware salient object detection method based on a Sample Adaptive View Transformer (SAVT) module with two sub-modules to mitigate these issues. Specifically, the sub-module View Transformer (VT) contains three transform branches based on different kinds of transformations to learn various features under different views and heighten the model's feature toleration of distortion, edge effects and object scales. Moreover, the sub-module Sample Adaptive Fusion (SAF) is to adjust the weights of different transform branches based on various sample features and make transformed enhanced features fuse more appropriately. The benchmark results of 20 state-of-the-art ISOD methods reveal the constructed dataset is very challenging. Moreover, exhaustive experiments verify the proposed approach is practical and outperforms the state-of-the-art methods.
Multi-Object Tracking over humans has improved rapidly with the development of object detection and re-identification. However, multi-actor tracking over humans with similar appearance and nonlinear movement can still be very challenging even for the state-of-the-art tracking algorithm. Current motion-based tracking algorithms often use Kalman Filter to predict the motion of an object, however, its linear movement assumption can cause failure in tracking when the target is not moving linearly. And for multi-players tracking over the sports field, because the players in the same team are usually wearing the same color of jersey, making re-identification even harder both in the short term and long term in the tracking process. In this work, we proposed a motionbased tracking algorithm and three post-processing pipelines for three sports including basketball, football, and volleyball, we successfully handle the tracking of the non-linear movement of players on the sports fields. Experiments result on the testing set of ECCV DeeperAction Challenge SportsMOT Dataset demonstrate the effectiveness of our method, which achieves a HOTA of 73.968, ranking 3rd place on the 2022 Sportsmot workshop final leaderboard.
Anomaly identification is highly dependent on the relationship between the object and the scene, as different/same object actions in same/different scenes may lead to various degrees of normality and anomaly. Therefore, object-scene relation actually plays a crucial role in anomaly detection but is inadequately explored in previous works. In this paper, we propose a Spatial-Temporal Relation Learning (STRL) framework to tackle the video anomaly detection task. First, considering dynamic characteristics of the objects as well as scene areas, we construct a Spatio-Temporal Auto-Encoder (STAE) to jointly exploit spatial and temporal evolution patterns for representation learning. For better pattern extraction, two decoding branches are designed in the STAE module, i.e. an appearance branch capturing spatial cues by directly predicting the next frame, and a motion branch focusing on modeling the dynamics via optical flow prediction. Then, to well concretize the object-scene relation, a Relation Learning (RL) module is devised to analyze and summarize the normal relations by introducing the Knowledge Graph Embedding methodology. Specifically in this process, the plausibility of object-scene relation is measured by jointly modeling object/scene features and optimizable object-scene relation maps. Extensive experiments are conducted on three public datasets, and the superior performance over the state-of-the-art methods demonstrates the effectiveness of our method.
Ensemble methods are a reliable way to combine several models to achieve superior performance. However, research on the application of ensemble methods in the remote sensing object detection scenario is mostly overlooked. Two problems arise. First, one unique characteristic of remote sensing object detection is the Oriented Bounding Boxes (OBB) of the objects and the fusion of multiple OBBs requires further research attention. Second, the widely used deep learning object detectors provide a score for each detected object as an indicator of confidence, but how to use these indicators effectively in an ensemble method remains a problem. Trying to address these problems, this paper proposes OBBStacking, an ensemble method that is compatible with OBBs and combines the detection results in a learned fashion. This ensemble method helps take 1st place in the Challenge Track \textit{Fine-grained Object Recognition in High-Resolution Optical Images}, which was featured in \textit{2021 Gaofen Challenge on Automated High-Resolution Earth Observation Image Interpretation}. The experiments on DOTA dataset and FAIR1M dataset demonstrate the improved performance of OBBStacking and the features of OBBStacking are analyzed.
To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth, existing multi-camera methods often generate multiple bounding boxes along a ray of depth direction for difficult small objects such as pedestrians, resulting in an extremely low recall. Furthermore, directly applying depth prediction modules to existing multi-camera methods, generally composed of large network architectures, cannot meet the real-time requirements of self-driving applications. To address these issues, we propose Cross-view and Depth-guided Transformers for 3D Object Detection, CrossDTR. First, our lightweight depth predictor is designed to produce precise object-wise sparse depth maps and low-dimensional depth embeddings without extra depth datasets during supervision. Second, a cross-view depth-guided transformer is developed to fuse the depth embeddings as well as image features from cameras of different views and generate 3D bounding boxes. Extensive experiments demonstrated that our method hugely surpassed existing multi-camera methods by 10 percent in pedestrian detection and about 3 percent in overall mAP and NDS metrics. Also, computational analyses showed that our method is 5 times faster than prior approaches. Our codes will be made publicly available at https://github.com/sty61010/CrossDTR.
The understanding of human-object interactions is fundamental in First Person Vision (FPV). Visual tracking algorithms which follow the objects manipulated by the camera wearer can provide useful information to effectively model such interactions. In the last years, the computer vision community has significantly improved the performance of tracking algorithms for a large variety of target objects and scenarios. Despite a few previous attempts to exploit trackers in the FPV domain, a methodical analysis of the performance of state-of-the-art trackers is still missing. This research gap raises the question of whether current solutions can be used ``off-the-shelf'' or more domain-specific investigations should be carried out. This paper aims to provide answers to such questions. We present the first systematic investigation of single object tracking in FPV. Our study extensively analyses the performance of 42 algorithms including generic object trackers and baseline FPV-specific trackers. The analysis is carried out by focusing on different aspects of the FPV setting, introducing new performance measures, and in relation to FPV-specific tasks. The study is made possible through the introduction of TREK-150, a novel benchmark dataset composed of 150 densely annotated video sequences. Our results show that object tracking in FPV poses new challenges to current visual trackers. We highlight the factors causing such behavior and point out possible research directions. Despite their difficulties, we prove that trackers bring benefits to FPV downstream tasks requiring short-term object tracking. We expect that generic object tracking will gain popularity in FPV as new and FPV-specific methodologies are investigated.
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc. Nonetheless, this direction has not been well-explored in comparison with models for outdoor environments (e.g., the autonomous driving system that includes pedestrian prediction, car detection, traffic sign recognition, etc.). In this paper, we first discuss the main challenge: insufficient, or even no, labeled data for real-world indoor environments, and other challenges such as fusion between heterogeneous sources of information (e.g., RGB images and Lidar point clouds), modeling relationships between a diverse set of outputs (e.g., 3D object locations, depth estimation, and human poses), and computational efficiency. Then, we describe MMISM (Multi-modality input Multi-task output Indoor Scene understanding Model) to tackle the above challenges. MMISM considers RGB images as well as sparse Lidar points as inputs and 3D object detection, depth completion, human pose estimation, and semantic segmentation as output tasks. We show that MMISM performs on par or even better than single-task models; e.g., we improve the baseline 3D object detection results by 11.7% on the benchmark ARKitScenes dataset.
We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, for scalability and quality. In total, we publicly release 272K manual semantic masks of 257 object classes, 9.9M interpolated dense masks, 67K hand-object relations, covering 36 hours of 179 untrimmed videos. Along with the annotations, we introduce three challenges in video object segmentation, interaction understanding and long-term reasoning. For data, code and leaderboards: http://epic-kitchens.github.io/VISOR
Purpose: Object detection is rapidly evolving through machine learning technology in automation systems. Well prepared data is necessary to train the algorithms. Accordingly, the objective of this paper is to describe a re-evaluation of the so-called Logistics Objects in Context (LOCO) dataset, which is the first dataset for object detection in the field of intralogistics. Methodology: We use an experimental research approach with three steps to evaluate the LOCO dataset. Firstly, the images on GitHub were analyzed to understand the dataset better. Secondly, Google Drive Cloud was used for training purposes to revisit the algorithmic implementation and training. Lastly, the LOCO dataset was examined, if it is possible to achieve the same training results in comparison to the original publications. Findings: The mean average precision, a common benchmark in object detection, achieved in our study was 64.54%, and shows a significant increase from the initial study of the LOCO authors, achieving 41%. However, improvement potential is seen specifically within object types of forklifts and pallet truck. Originality: This paper presents the first critical replication study of the LOCO dataset for object detection in intralogistics. It shows that the training with better hyperparameters based on LOCO can even achieve a higher accuracy than presented in the original publication. However, there is also further room for improving the LOCO dataset.
Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation. When a teacher provides an instruction to a learner about an object by referring to its features, the learner can misunderstand the teacher's intentions, for instance if the instruction ambiguously refer to features of the object, a phenomenon called referential ambiguity. We study how two concepts derived from cognitive sciences can help resolve those referential ambiguities: pedagogy (selecting the right instructions) and pragmatism (learning the preferences of the other agents using inductive reasoning). We apply those ideas to a teacher/learner setup with two artificial agents on a simulated robotic task (block-stacking). We show that these concepts improve sample efficiency for training the learner.
In this work, we tackle the challenging task of jointly tracking hand object pose and reconstructing their shapes from depth point cloud sequences in the wild, given the initial poses at frame 0. We for the first time propose a point cloud based hand joint tracking network, HandTrackNet, to estimate the inter-frame hand joint motion. Our HandTrackNet proposes a novel hand pose canonicalization module to ease the tracking task, yielding accurate and robust hand joint tracking. Our pipeline then reconstructs the full hand via converting the predicted hand joints into a template-based parametric hand model MANO. For object tracking, we devise a simple yet effective module that estimates the object SDF from the first frame and performs optimization-based tracking. Finally, a joint optimization step is adopted to perform joint hand and object reasoning, which alleviates the occlusion-induced ambiguity and further refines the hand pose. During training, the whole pipeline only sees purely synthetic data, which are synthesized with sufficient variations and by depth simulation for the ease of generalization. The whole pipeline is pertinent to the generalization gaps and thus directly transferable to real in-the-wild data. We evaluate our method on two real hand object interaction datasets, e.g. HO3D and DexYCB, without any finetuning. Our experiments demonstrate that the proposed method significantly outperforms the previous state-of-the-art depth-based hand and object pose estimation and tracking methods, running at a frame rate of 9 FPS.