자율 무인 잠수정(AUV)은 연구, 에너지, 국방에 이르는 다양한 산업 분야에서 점점 더 중요해지고 있는 도구입니다. AUV는 고정된 배터리 용량을 가지고 원격 환경에서 운용되는 전력 제약적인 플랫폼으로, 장시간의 임무 수행 동안 추진 시스템이 컴퓨팅 및 센서와 전력을 두고 경쟁합니다. AUV는 광학 감지의 활용 가치가 제한적인 어둡거나 탁한 수중에서 자주 운용되며, 주요 감지 방식으로 소나에 의존합니다. 합성곱 신경망(CNN)은 전방 주시 소나(Forward-Looking Sonar, FLS) 영상의 객체 검출(object detection) 분야에서 최고 수준(state-of-the-art)의 솔루션이지만, 에너지 소모가 큽니다(예: YOLOv8m의 경우 추론당 322 mJ). 스파이킹 신경망(SNN)은 이진 스파이크 활성화와 이에 따른 희소한 누적 전용 연산에 의존하므로, 특히 전용 뉴로모픽 하드웨어와 결합될 때 매우 뛰어난 에너지 효율을 제공할 수 있습니다. 전방 주시 소나 반사 신호의 희소하고 대비가 높은 구조는 광학 영상과 달리 스파이크 코딩에 구조적으로 잘 부합합니다. 이전 연구에서는 FLS 영상의 객체 검출에 대한 SNN의 적합성을 평가한 바가 없습니다. 대리 기울기(surrogate gradients)로 학습된 완전 스파이킹 네트워크인 SpikeYOLO는 세 가지 FLS 객체 검출 데이터셋(dataset)에서 최첨단 CNN 베이스라인과 비교 벤치마킹되었습니다. 주요 결과: SpikeYOLO T=2는 UATD에서 경쟁력 있는 정확도(YOLOv8m의 0.575 대비 0.529 [email omitted]:0.95)를 유지하면서 3.3배 낮은 이론적 연산 에너지(322 mJ 대비 97 mJ)를 달성합니다. SpikeYOLO는 희소한 Marine-Debris-FLS 데이터셋에서 [email omitted] 기준으로 YOLOv8m과 동등한 성능을 보이며, 4.4배 낮은 에너지로 YOLO-SONAR 및 Fast R-CNN 베이스라인을 능가합니다. SpikeYOLO는 승법 스펙클 노이즈(multiplicative speckle noise)에 대해 우수한 강건성을 입증하며($σ=0.4$에서 YOLOv8m의 8.9% 저하 대비 3.0% 저하), $σ=0.6$에서는 YOLOv8m을 완전히 능가하여 실제 FLS 배포와 직접적인 관련성을 보여줍니다.
Conventional object detection models are usually limited by the data on which they were trained and by the category logic they define. With the recent rise of Language-Visual Models, new methods have emerged that are not restricted to these fixed categories. Despite their flexibility, such Open Vocabulary detection models still fall short in accuracy compared to traditional models with fixed classes. At the same time, more accurate data-specific models face challenges when there is a need to extend classes or merge different datasets for training. The latter often cannot be combined due to different logics or conflicting class definitions, making it difficult to improve a model without compromising its performance. In this paper, we introduce CerberusDet, a framework with a multi-headed model designed for handling multiple object detection tasks. Proposed model is built on the YOLO architecture and efficiently shares visual features from both backbone and neck components, while maintaining separate task heads. This approach allows CerberusDet to perform very efficiently while still delivering optimal results. We evaluated the model on the PASCAL VOC dataset and Objects365 dataset to demonstrate its abilities. CerberusDet achieved state-of-the-art results with 36% less inference time. The more tasks are trained together, the more efficient the proposed model becomes compared to running individual models sequentially. The training and inference code, as well as the model, are available as open-source (https://github.com/ai-forever/CerberusDet).
Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: https://github.com/JDAI-CV/LIO.
Traditional Scene Understanding problems such as Object Detection and Semantic Segmentation have made breakthroughs in recent years due to the adoption of deep learning. However, the former task is not able to localise objects at a pixel level, and the latter task has no notion of different instances of objects of the same class. We focus on the task of Instance Segmentation which recognises and localises objects down to a pixel level. Our model is based on a deep neural network trained for semantic segmentation. This network incorporates a Conditional Random Field with end-to-end trainable higher order potentials based on object detector outputs. This allows us to reason about instances from an initial, category-level semantic segmentation. Our simple method effectively leverages the great progress recently made in semantic segmentation and object detection. The accurate instance-level segmentations that our network produces is reflected by the considerable improvements obtained over previous work.
Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions ("things and stuff") in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.
Extrinsic perturbation always exists in multiple sensors. In this paper, we focus on the extrinsic uncertainty in multi-LiDAR systems for 3D object detection. We first analyze the influence of extrinsic perturbation on geometric tasks with two basic examples. To minimize the detrimental effect of extrinsic perturbation, we propagate an uncertainty prior on each point of input point clouds, and use this information to boost an approach for 3D geometric tasks. Then we extend our findings to propose a multi-LiDAR 3D object detector called MLOD. MLOD is a two-stage network where the multi-LiDAR information is fused through various schemes in stage one, and the extrinsic perturbation is handled in stage two. We conduct extensive experiments on a real-world dataset, and demonstrate both the accuracy and robustness improvement of MLOD. The code, data and supplementary materials are available at: https://ram-lab.com/file/site/mlod
Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences. The proposed model comprises a spatial feature encoding component and a spatiotemporal feature aggregation component. In the former component, a novel Pillar Message Passing Network (PMPNet) is proposed to encode each discrete point cloud frame. It adaptively collects information for a pillar node from its neighbors by iterative message passing, which effectively enlarges the receptive field of the pillar feature. In the latter component, we propose an Attentive Spatiotemporal Transformer GRU (AST-GRU) to aggregate the spatiotemporal information, which enhances the conventional ConvGRU with an attentive memory gating mechanism. AST-GRU contains a Spatial Transformer Attention (STA) module and a Temporal Transformer Attention (TTA) module, which can emphasize the foreground objects and align the dynamic objects, respectively. Experimental results demonstrate that the proposed 3D video object detector achieves state-of-the-art performance on the large-scale nuScenes benchmark.
In human-robot collaboration, one challenging task is to teach a robot new yet unknown objects enabling it to interact with them. Thereby, gaze can contain valuable information. We investigate if it is possible to detect objects (object or no object) merely from gaze data and determine their bounding box parameters. For this purpose, we explore different sizes of temporal windows, which serve as a basis for the computation of heatmaps, i.e., the spatial distribution of the gaze data. Additionally, we analyze different grid sizes of these heatmaps, and demonstrate the functionality in a proof of concept using different machine learning techniques. Our method is characterized by its speed and resource efficiency compared to conventional object detectors. In order to generate the required data, we conducted a study with five subjects who could move freely and thus, turn towards arbitrary objects. This way, we chose a scenario for our data collection that is as realistic as possible. Since the subjects move while facing objects, the heatmaps also contain gaze data trajectories, complicating the detection and parameter regression. We make our data set publicly available to the research community for download.
Although the majority of recent autonomous driving systems concentrate on developing perception methods based on ego-vehicle sensors, there is an overlooked alternative approach that involves leveraging intelligent roadside cameras to help extend the ego-vehicle perception ability beyond the visual range. We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground. However, the roadside camera is installed on a pole with a pitched angle, which makes the existing methods not optimal for roadside scenes. In this paper, we introduce a novel framework for Roadside Monocular 3D object detection with ground-aware embeddings, named MonoGAE. Specifically, the ground plane is a stable and strong prior knowledge due to the fixed installation of cameras in roadside scenarios. In order to reduce the domain gap between the ground geometry information and high-dimensional image features, we employ a supervised training paradigm with a ground plane to predict high-dimensional ground-aware embeddings. These embeddings are subsequently integrated with image features through cross-attention mechanisms. Furthermore, to improve the detector's robustness to the divergences in cameras' installation poses, we replace the ground plane depth map with a novel pixel-level refined ground plane equation map. Our approach demonstrates a substantial performance advantage over all previous monocular 3D object detectors on widely recognized 3D detection benchmarks for roadside cameras. The code and pre-trained models will be released soon.
The proliferation of smartphones and other mobile devices provides a unique opportunity to make Advanced Driver Assistance Systems (ADAS) accessible to everyone in the form of an application empowered by low-cost Machine/Deep Learning (ML/DL) models to enhance road safety. For the critical feature of Collision Avoidance in Mobile ADAS, lightweight Deep Neural Networks (DNN) for object detection exist, but conventional pixel-wise depth/distance estimation DNNs are vastly more computationally expensive making them unsuitable for a real-time application on resource-constrained devices. In this paper, we present a distance estimation model, DECADE, that processes each detector output instead of constructing pixel-wise depth/disparity maps. In it, we propose a pose estimation DNN to estimate allocentric orientation of detections to supplement the distance estimation DNN in its prediction of distance using bounding box features. We demonstrate that these modules can be attached to any detector to extend object detection with fast distance estimation. Evaluation of the proposed modules with attachment to and fine-tuning on the outputs of the YOLO object detector on the KITTI 3D Object Detection dataset achieves state-of-the-art performance with 1.38 meters in Mean Absolute Error and 7.3% in Mean Relative Error in the distance range of 0-150 meters. Our extensive evaluation scheme not only evaluates class-wise performance, but also evaluates range-wise accuracy especially in the critical range of 0-70m.
Determining the relative pose of a previously unseen object between two images is pivotal to the success of generalizable object pose estimation. Existing approaches typically predict 3D translation utilizing the ground-truth object bounding box and approximate 3D rotation with a large number of discrete hypotheses. This strategy makes unrealistic assumptions about the availability of ground truth and incurs a computationally expensive process of scoring each hypothesis at test time. By contrast, we rethink the problem of relative pose estimation for unseen objects by presenting a Deep Voxel Matching Network (DVMNet++). Our method computes the relative object pose in a single pass, eliminating the need for ground-truth object bounding boxes and rotation hypotheses. We achieve open-set object detection by leveraging image feature embedding and natural language understanding as reference. The detection result is then employed to approximate the translation parameters and crop the object from the query image. For rotation estimation, we map the two RGB images, i.e., reference and cropped query, to their respective voxelized 3D representations. The resulting voxels are passed through a rotation estimation module, which aligns the voxels and computes the rotation in an end-to-end fashion by solving a least-squares problem. To enhance robustness, we introduce a weighted closest voxel algorithm capable of mitigating the impact of noisy voxels. We conduct extensive experiments on the CO3D, Objaverse, LINEMOD, and LINEMOD-O datasets, demonstrating that our approach delivers more accurate relative pose estimates for novel objects at a lower computational cost compared to state-of-the-art methods. Our code is released at https://github.com/sailor-z/DVMNet/.
Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks. In order to obtain stronger semantic feature, we adopt ResNet as feature extraction layers and exploit multi-level feature by combining hierarchical convolutional networks. A vertical proposal mechanism is utilized to avoid proposal classification, while regression layer remains working to improve localization accuracy. Our approach evaluated on ICDAR2013 dataset achieves F-measure of 0.91, which outperforms previous state-of-the-art results in scene text detection.
We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of oriented gradient (COG) descriptor that links the 2D appearance and 3D pose of object categories, and thus accurately models how perspective projection affects perceived image gradients. To better represent the 3D visual styles of large objects and provide contextual cues to improve the detection of small objects, we introduce latent support surfaces. We then propose a "Manhattan voxel" representation which better captures the 3D room layout geometry of common indoor environments. Effective classification rules are learned via a latent structured prediction framework. Contextual relationships among categories and layout are captured via a cascade of classifiers, leading to holistic scene hypotheses that exceed the state-of-the-art on the SUN RGB-D database.
We develop a probabilistic interpretation of two-stage object detection. We show that this probabilistic interpretation motivates a number of common empirical training practices. It also suggests changes to two-stage detection pipelines. Specifically, the first stage should infer proper object-vs-background likelihoods, which should then inform the overall score of the detector. A standard region proposal network (RPN) cannot infer this likelihood sufficiently well, but many one-stage detectors can. We show how to build a probabilistic two-stage detector from any state-of-the-art one-stage detector. The resulting detectors are faster and more accurate than both their one- and two-stage precursors. Our detector achieves 56.4 mAP on COCO test-dev with single-scale testing, outperforming all published results. Using a lightweight backbone, our detector achieves 49.2 mAP on COCO at 33 fps on a Titan Xp, outperforming the popular YOLOv4 model.
In this paper, we propose SpotNet: a fast, single stage, image-centric but LiDAR anchored approach for long range 3D object detection. We demonstrate that our approach to LiDAR/image sensor fusion, combined with the joint learning of 2D and 3D detection tasks, can lead to accurate 3D object detection with very sparse LiDAR support. Unlike more recent bird's-eye-view (BEV) sensor-fusion methods which scale with range $r$ as $O(r^2)$, SpotNet scales as $O(1)$ with range. We argue that such an architecture is ideally suited to leverage each sensor's strength, i.e. semantic understanding from images and accurate range finding from LiDAR data. Finally we show that anchoring detections on LiDAR points removes the need to regress distances, and so the architecture is able to transfer from 2MP to 8MP resolution images without re-training.
In this paper, we propose a novel and highly practical score-level fusion approach called dynamic belief fusion (DBF) that directly integrates inference scores of individual detections from multiple object detection methods. To effectively integrate the individual outputs of multiple detectors, the level of ambiguity in each detection score is estimated using a confidence model built on a precision-recall relationship of the corresponding detector. For each detector output, DBF then calculates the probabilities of three hypotheses (target, non-target, and intermediate state (target or non-target)) based on the confidence level of the detection score conditioned on the prior confidence model of individual detectors, which is referred to as basic probability assignment. The probability distributions over three hypotheses of all the detectors are optimally fused via the Dempster's combination rule. Experiments on the ARL, PASCAL VOC 07, and 12 datasets show that the detection accuracy of the DBF is significantly higher than any of the baseline fusion approaches as well as individual detectors used for the fusion.
본 논문에서는 우리가 아는 한 최초의 실시간 지향성 검출 트랜스포머(oriented detection transformer)인 RiO-DETR(실시간 지향성 객체 검출을 위한 DETR)을 제시합니다. DETR을 지향성 바운딩 박스(oriented bounding boxes, OBB)에 적용하는 데에는 세 가지 과제가 따릅니다. 의미론에 의존적인 방향성, 표준 유클리드 정제를 무너뜨리는 각도의 주기성, 그리고 수렴 속도를 늦추는 확장된 탐색 공간입니다. RiO-DETR은 실시간 효율성을 유지하면서 작업 고유의 설계를 통해 이러한 문제를 해결합니다. 첫째, 위치 쿼리에서 각도를 분리하는 콘텐츠 기반 각도 추정(Content-Driven Angle Estimation)과 신뢰할 수 있는 방향성을 포착하기 위해 상호보완적 단서를 포착하는 회전 보정 직교 어텐션(Rotation-Rectified Orthogonal Attention)을 제안합니다. 둘째, 분리된 주기적 정제(Decoupled Periodic Refinement)는 제한된 coarse-to-fine 업데이트와 최단 경로 주기적 손실(Shortest-Path Periodic Loss)을 결합하여 각도 경계 전반에서 안정적인 학습을 가능하게 합니다. 셋째, Oriented Dense O2O는 조밀한 지도(dense supervision)에 각도 다양성을 주입하여 추가적인 비용 없이 각도 수렴을 가속화합니다. DOTA-1.0, DIOR-R, FAIR-1M-2.0에 대한 광범위한 실험을 통해 RiO-DETR이 실시간 지향성 객체 검출에서 새로운 속도-정확도 트레이드오프를 확립함을 입증합니다. GitHub 저장소: https://github.com/RicePasteM/RiO-DETR.
Marine debris is a problem both for the health of marine environments and for the human health since tiny pieces of plastic called "microplastics" resulting from the debris decomposition over the time are entering the food chain at any levels. For marine debris detection and removal, autonomous underwater vehicles (AUVs) are a potential solution. In this letter, we focus on the efficiency of AUV vision for real-time and low-light object detection. First, we improved the efficiency of a class of state-of-the-art object detectors, namely EfficientDets, by 1.5% AP on D0, 2.6% AP on D1, 1.2% AP on D2 and 1.3% AP on D3 without increasing the GPU latency. Subsequently, we created and made publicly available a dataset for the detection of in-water plastic bags and bottles and trained our improved EfficientDets on this and another dataset for marine debris detection. Finally, we investigated how the detector performance is affected by low-light conditions and compared two low-light underwater image enhancement strategies both in terms of accuracy and latency. Source code and dataset are publicly available.
In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022. For multi-view camera-only 3D detection, methods based on bird-eye-view or 3D geometric representations can leverage the stereo cues from overlapped regions between adjacent views and directly perform 3D detection without hand-crafted post-processing. However, it lacks direct semantic supervision for 2D backbones, which can be complemented by pretraining simple monocular-based detectors. Our solution is a multi-view framework for 4D detection following this paradigm. It is built upon a simple monocular detector FCOS3D++, pretrained only with object annotations of Waymo, and converts multi-view features to a 3D grid space to detect 3D objects thereon. A dual-path neck for single-frame understanding and temporal stereo matching is devised to incorporate multi-frame information. Our method finally achieves 49.75% mAPL with a single model and wins 2nd place in the WOD challenge, without any LiDAR-based depth supervision during training. The code will be released at https://github.com/Tai-Wang/Depth-from-Motion.
In this paper, we propose several novel deep learning methods for object saliency detection based on the powerful convolutional neural networks. In our approach, we use a gradient descent method to iteratively modify an input image based on the pixel-wise gradients to reduce a cost function measuring the class-specific objectness of the image. The pixel-wise gradients can be efficiently computed using the back-propagation algorithm. The discrepancy between the modified image and the original one may be used as a saliency map for the image. Moreover, we have further proposed several new training methods to learn saliency-specific convolutional nets for object saliency detection, in order to leverage the available pixel-wise segmentation information. Our methods are extremely computationally efficient (processing 20-40 images per second in one GPU). In this work, we use the computed saliency maps for image segmentation. Experimental results on two benchmark tasks, namely Microsoft COCO and Pascal VOC 2012, have shown that our proposed methods can generate high-quality salience maps, clearly outperforming many existing methods. In particular, our approaches excel in handling many difficult images, which contain complex background, highly-variable salient objects, multiple objects, and/or very small salient objects.