It is critical for vehicles to prevent any collisions with pedestrians. Current methods for pedestrian collision prevention focus on integrating visual pedestrian detectors with Automatic Emergency Braking (AEB) systems which can trigger warnings and apply brakes as a pedestrian enters a vehicle's path. Unfortunately, pedestrian-detection-based systems can be hindered in certain situations such as night-time or when pedestrians are occluded. Our system addresses such issues using an online, map-based pedestrian detection aggregation system where common pedestrian locations are learned after repeated passes of locations. Using a carefully collected and annotated dataset in La Jolla, CA, we demonstrate the system's ability to learn pedestrian zones and generate advisory notices when a vehicle is approaching a pedestrian despite challenges like dark lighting or pedestrian occlusion. Using the number of correct advisories, false advisories, and missed advisories to define precision and recall performance metrics, we evaluate our system and discuss future positive effects with further data collection. We have made our code available at //github.com/s7desai/ped-mapping, and a video demonstration of the CHAMP system at //youtu.be/dxeCrS_Gpkw.
相關內容
Robust detection of vulnerable road users is a safety critical requirement for the deployment of autonomous vehicles in heterogeneous traffic. One of the most complex outstanding challenges is that of partial occlusion where a target object is only partially available to the sensor due to obstruction by another foreground object. A number of leading pedestrian detection benchmarks provide annotation for partial occlusion, however each benchmark varies greatly in their definition of the occurrence and severity of occlusion. Recent research demonstrates that a high degree of subjectivity is used to classify occlusion level in these cases and occlusion is typically categorized into 2 to 3 broad categories such as partially and heavily occluded. This can lead to inaccurate or inconsistent reporting of pedestrian detection model performance depending on which benchmark is used. This research introduces a novel, objective benchmark for partially occluded pedestrian detection to facilitate the objective characterization of pedestrian detection models. Characterization is carried out on seven popular pedestrian detection models for a range of occlusion levels from 0-99%, in order to demonstrate the efficacy and increased analysis capabilities of the proposed characterization method. Results demonstrate that pedestrian detection performance degrades, and the number of false negative detections increase as pedestrian occlusion level increases. Of the seven popular pedestrian detection routines characterized, CenterNet has the greatest overall performance, followed by SSDlite. RetinaNet has the lowest overall detection performance across the range of occlusion levels.
The advent of data-driven technology solutions is accompanied by an increasing concern with data privacy. This is of particular importance for human-centered image recognition tasks, such as pedestrian detection, re-identification, and tracking. To highlight the importance of privacy issues and motivate future research, we motivate and introduce the Pedestrian Dataset De-Identification (PDI) task. PDI evaluates the degree of de-identification and downstream task training performance for a given de-identification method. As a first baseline, we propose IncogniMOT, a two-stage full-body de-identification pipeline based on image synthesis via generative adversarial networks. The first stage replaces target pedestrians with synthetic identities. To improve downstream task performance, we then apply stage two, which blends and adapts the synthetic image parts into the data. To demonstrate the effectiveness of IncogniMOT, we generate a fully de-identified version of the MOT17 pedestrian tracking dataset and analyze its application as training data for pedestrian re-identification, detection, and tracking models. Furthermore, we show how our data is able to narrow the synthetic-to-real performance gap in a privacy-conscious manner.
This work aims to address the challenges in domain adaptation of 3D object detection using infrastructure LiDARs. We design a model DASE-ProPillars that can detect vehicles in infrastructure-based LiDARs in real-time. Our model uses PointPillars as the baseline model with additional modules to improve the 3D detection performance. To prove the effectiveness of our proposed modules in DASE-ProPillars, we train and evaluate the model on two datasets, the open source A9-Dataset and a semi-synthetic infrastructure dataset created within the Regensburg Next project. We do several sets of experiments for each module in the DASE-ProPillars detector that show that our model outperforms the SE-ProPillars baseline on the real A9 test set and a semi-synthetic A9 test set, while maintaining an inference speed of 45 Hz (22 ms). We apply domain adaptation from the semi-synthetic A9-Dataset to the semi-synthetic dataset from the Regensburg Next project by applying transfer learning and achieve a 3D [email protected] of 93.49% on the Car class of the target test set using 40 recall positions.
We contribute the Habitat Synthetic Scene Dataset, a dataset of 211 high-quality 3D scenes, and use it to test navigation agent generalization to realistic 3D environments. Our dataset represents real interiors and contains a diverse set of 18,656 models of real-world objects. We investigate the impact of synthetic 3D scene dataset scale and realism on the task of training embodied agents to find and navigate to objects (ObjectGoal navigation). By comparing to synthetic 3D scene datasets from prior work, we find that scale helps in generalization, but the benefits quickly saturate, making visual fidelity and correlation to real-world scenes more important. Our experiments show that agents trained on our smaller-scale dataset can match or outperform agents trained on much larger datasets. Surprisingly, we observe that agents trained on just 122 scenes from our dataset outperform agents trained on 10,000 scenes from the ProcTHOR-10K dataset in terms of zero-shot generalization in real-world scanned environments.
Most autonomous navigation systems assume wheeled robots are rigid bodies and their 2D planar workspaces can be divided into free spaces and obstacles. However, recent wheeled mobility research, showing that wheeled platforms have the potential of moving over vertically challenging terrain (e.g., rocky outcroppings, rugged boulders, and fallen tree trunks), invalidate both assumptions. Navigating off-road vehicle chassis with long suspension travel and low tire pressure in places where the boundary between obstacles and free spaces is blurry requires precise 3D modeling of the interaction between the chassis and the terrain, which is complicated by suspension and tire deformation, varying tire-terrain friction, vehicle weight distribution and momentum, etc. In this paper, we present a learning approach to model wheeled mobility, i.e., in terms of vehicle-terrain forward dynamics, and plan feasible, stable, and efficient motion to drive over vertically challenging terrain without rolling over or getting stuck. We present physical experiments on two wheeled robots and show that planning using our learned model can achieve up to 60% improvement in navigation success rate and 46% reduction in unstable chassis roll and pitch angles.
Skin cancer is a major public health problem that could benefit from computer-aided diagnosis to reduce the burden of this common disease. Skin lesion segmentation from images is an important step toward achieving this goal. However, the presence of natural and artificial artifacts (e.g., hair and air bubbles), intrinsic factors (e.g., lesion shape and contrast), and variations in image acquisition conditions make skin lesion segmentation a challenging task. Recently, various researchers have explored the applicability of deep learning models to skin lesion segmentation. In this survey, we cross-examine 177 research papers that deal with deep learning-based segmentation of skin lesions. We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance). We discuss these dimensions both from the viewpoint of select seminal works, and from a systematic viewpoint, examining how those choices have influenced current trends, and how their limitations should be addressed. To facilitate comparisons, we summarize all examined works in a comprehensive table as well as an interactive table available online at //github.com/sfu-mial/skin-lesion-segmentation-survey.
This paper introduces Artificial Intelligence Clinics on Mobile (AICOM), an open-source project devoted to answering the United Nations Sustainable Development Goal 3 (SDG3) on health, which represents a universal recognition that health is fundamental to human capital and social and economic development. The core motivation for the AICOM project is the fact that over 80% of the people in the least developed countries (LDCs) own a mobile phone, even though less than 40% of these people have internet access. Hence, through enabling AI-based disease diagnostics and screening capability on affordable mobile phones without connectivity will be a critical first step to addressing healthcare access problems. The technologies developed in the AICOM project achieve exactly this goal, and we have demonstrated the effectiveness of AICOM on monkeypox screening tasks. We plan to continue expanding and open-sourcing the AICOM platform, aiming for it to evolve into an universal AI doctor for the Underserved and Hard-to-Reach.
Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification, detection, and segmentation, they fundamentally are unable to generalize to an ever-evolving world due to constant out-of-distribution shifts of input data. Therefore, instead of training on fixed datasets, can we approach learning in a more human-centric and adaptive manner? In this paper, we introduce \textbf{A}ction-aware Embodied \textbf{L}earning for \textbf{P}erception (ALP), an embodied learning framework that incorporates action information into representation learning through a combination of optimizing policy gradients through reinforcement learning and inverse dynamics prediction objectives. Our method actively explores complex 3D environments to both learn generalizable task-agnostic representations as well as collect downstream training data. We show that ALP outperforms existing baselines in object detection and semantic segmentation. In addition, we show that by training on actively collected data more relevant to the environment and task, our method generalizes more robustly to downstream tasks compared to models pre-trained on fixed datasets such as ImageNet.
Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate whether it is possible to leverage domain information from the unseen test samples themselves. We propose a domain-adaptive approach consisting of two steps: a) we first learn a discriminative domain embedding from unsupervised training examples, and b) use this domain embedding as supplementary information to build a domain-adaptive model, that takes both the input as well as its domain into account while making predictions. For unseen domains, our method simply uses few unlabelled test examples to construct the domain embedding. This enables adaptive classification on any unseen domain. Our approach achieves state-of-the-art performance on various domain generalization benchmarks. In addition, we introduce the first real-world, large-scale domain generalization benchmark, Geo-YFCC, containing 1.1M samples over 40 training, 7 validation, and 15 test domains, orders of magnitude larger than prior work. We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains. In contrast, our approach achieves a significant improvement.
Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191