We present a method to track the precise shape of an object in video based on new modeling and optimization on a new Riemannian manifold of parameterized regions. Joint dynamic shape and appearance models, in which a template of the object is propagated to match the object shape and radiance in the next frame, are advantageous over methods employing global image statistics in cases of complex object radiance and cluttered background. In cases of 3D object motion and viewpoint change, self-occlusions and dis-occlusions of the object are prominent, and current methods employing joint shape and appearance models are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the template are coupled, thus a joint problem is formulated. We derive a coarse-to-fine optimization scheme, advantageous in object tracking, that initially perturbs the template by coarse perturbations before transitioning to finer-scale perturbations, traversing all scales, seamlessly and automatically. The scheme is a gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev-type metric defined on infinitesimal vector fields on regions. The metric has the property of resulting in a gradient descent that automatically favors coarse-scale deformations (when they reduce the energy) before moving to finer-scale deformations. Experiments on video exhibiting occlusion/dis-occlusion, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy compared to recent methods employing joint shape/appearance models or employing global statistics.
Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by DETR, which excels in object detection, we view scene graph generation as a set prediction problem and propose an end-to-end scene graph generation model RelTR which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts a set of relationships directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome and Open Images V6 datasets demonstrate the superior performance and fast inference of our model.
Unmanned Aerial Vehicles (UAV) can pose a major risk for aviation safety, due to both negligent and malicious use. For this reason, the automated detection and tracking of UAV is a fundamental task in aerial security systems. Common technologies for UAV detection include visible-band and thermal infrared imaging, radio frequency and radar. Recent advances in deep neural networks (DNNs) for image-based object detection open the possibility to use visual information for this detection and tracking task. Furthermore, these detection architectures can be implemented as backbones for visual tracking systems, thereby enabling persistent tracking of UAV incursions. To date, no comprehensive performance benchmark exists that applies DNNs to visible-band imagery for UAV detection and tracking. To this end, three datasets with varied environmental conditions for UAV detection and tracking, comprising a total of 241 videos (331,486 images), are assessed using four detection architectures and three tracking frameworks. The best performing detector architecture obtains an mAP of 98.6% and the best performing tracking framework obtains a MOTA of 96.3%. Cross-modality evaluation is carried out between visible and infrared spectrums, achieving a maximal 82.8% mAP on visible images when training in the infrared modality. These results provide the first public multi-approach benchmark for state-of-the-art deep learning-based methods and give insight into which detection and tracking architectures are effective in the UAV domain.
Previous works on unsupervised industrial anomaly detection mainly focus on local structural anomalies such as cracks and color contamination. While achieving significantly high detection performance on this kind of anomaly, they are faced with logical anomalies that violate the long-range dependencies such as a normal object placed in the wrong position. In this paper, based on previous knowledge distillation works, we propose to use two students (local and global) to better mimic the teacher's behavior. The local student, which is used in previous studies mainly focuses on structural anomaly detection while the global student pays attention to logical anomalies. To further encourage the global student's learning to capture long-range dependencies, we design the global context condensing block (GCCB) and propose a contextual affinity loss for the student training and anomaly scoring. Experimental results show the proposed method doesn't need cumbersome training techniques and achieves a new state-of-the-art performance on the MVTec LOCO AD dataset.
FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, including object detection and instance segmentation, have not been adequately addressed. Compared with image classification, detection problems are more sensitive to the spatial variance of objects, and therefore, require specialized convolutions to aggregate spatial information. To address this, recent work proposes dynamic deformable convolution to augment regular convolutions. Regular convolutions process a fixed grid of pixels across all the spatial locations in an image, while dynamic deformable convolutions may access arbitrary pixels in the image and the access pattern is input-dependent and varies per spatial location. These properties lead to inefficient memory accesses of inputs with existing hardware. In this work, we first investigate the overhead of the deformable convolution on embedded FPGA SoCs, and then show the accuracy-latency tradeoffs for a set of algorithm modifications including full versus depthwise, fixed-shape, and limited-range. These modifications benefit the energy efficiency for embedded devices in general as they reduce the compute complexity. We then build an efficient object detection network with modified deformable convolutions and quantize the network using state-of-the-art quantization methods. We implement a unified hardware engine on FPGA to support all the operations in the network. Preliminary experiments show that little accuracy is compromised and speedup can be achieved with our co-design optimization for the deformable convolution.
Camouflaged object detection (COD), which aims to identify the objects that conceal themselves into the surroundings, has recently drawn increasing research efforts in the field of computer vision. In practice, the success of deep learning based COD is mainly determined by two key factors, including (i) A significantly large receptive field, which provides rich context information, and (ii) An effective fusion strategy, which aggregates the rich multi-level features for accurate COD. Motivated by these observations, in this paper, we propose a novel deep learning based COD approach, which integrates the large receptive field and effective feature fusion into a unified framework. Specifically, we first extract multi-level features from a backbone network. The resulting features are then fed to the proposed dual-branch mixture convolution modules, each of which utilizes multiple asymmetric convolutional layers and two dilated convolutional layers to extract rich context features from a large receptive field. Finally, we fuse the features using specially-designed multilevel interactive fusion modules, each of which employs an attention mechanism along with feature interaction for effective feature fusion. Our method detects camouflaged objects with an effective fusion strategy, which aggregates the rich context information from a large receptive field. All of these designs meet the requirements of COD well, allowing the accurate detection of camouflaged objects. Extensive experiments on widely-used benchmark datasets demonstrate that our method is capable of accurately detecting camouflaged objects and outperforms the state-of-the-art methods.
State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such 3D data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only, RGB-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings. Our code is available at https://github.com/meharkhurana03/cm3d
Object parsing -- the task of decomposing an object into its semantic parts -- has traditionally been formulated as a category-level segmentation problem. Consequently, when there are multiple objects in an image, current methods cannot count the number of objects in the scene, nor can they determine which part belongs to which object. We address this problem by segmenting the parts of objects at an instance-level, such that each pixel in the image is assigned a part label, as well as the identity of the object it belongs to. Moreover, we show how this approach benefits us in obtaining segmentations at coarser granularities as well. Our proposed network is trained end-to-end given detections, and begins with a category-level segmentation module. Thereafter, a differentiable Conditional Random Field, defined over a variable number of instances for every input image, reasons about the identity of each part by associating it with a human detection. In contrast to other approaches, our method can handle the varying number of people in each image and our holistic network produces state-of-the-art results in instance-level part and human segmentation, together with competitive results in category-level part segmentation, all achieved by a single forward-pass through our neural network.
Unavailability of large training datasets is a bottleneck that needs to be overcome to realize the true potential of deep learning in histopathology applications. Although slide digitization via whole slide imaging scanners has increased the speed of data acquisition, labeling of virtual slides requires a substantial time investment from pathologists. Eye gaze annotations have the potential to speed up the slide labeling process. This work explores the viability and timing comparisons of eye gaze labeling compared to conventional manual labeling for training object detectors. Challenges associated with gaze based labeling and methods to refine the coarse data annotations for subsequent object detection are also discussed. Results demonstrate that gaze tracking based labeling can save valuable pathologist time and delivers good performance when employed for training a deep object detector. Using the task of localization of Keratin Pearls in cases of oral squamous cell carcinoma as a test case, we compare the performance gap between deep object detectors trained using hand-labelled and gaze-labelled data. On average, compared to `Bounding-box' based hand-labeling, gaze-labeling required $57.6\%$ less time per label and compared to `Freehand' labeling, gaze-labeling required on average $85\%$ less time per label.
Zero-shot 6D object pose estimation involves the detection of novel objects with their 6D poses in cluttered scenes, presenting significant challenges for model generalizability. Fortunately, the recent Segment Anything Model (SAM) has showcased remarkable zero-shot transfer performance, which provides a promising solution to tackle this task. Motivated by this, we introduce SAM-6D, a novel framework designed to realize the task through two steps, including instance segmentation and pose estimation. Given the target objects, SAM-6D employs two dedicated sub-networks, namely Instance Segmentation Model (ISM) and Pose Estimation Model (PEM), to perform these steps on cluttered RGB-D images. ISM takes SAM as an advanced starting point to generate all possible object proposals and selectively preserves valid ones through meticulously crafted object matching scores in terms of semantics, appearance and geometry. By treating pose estimation as a partial-to-partial point matching problem, PEM performs a two-stage point matching process featuring a novel design of background tokens to construct dense 3D-3D correspondence, ultimately yielding the pose estimates. Without bells and whistles, SAM-6D outperforms the existing methods on the seven core datasets of the BOP Benchmark for both instance segmentation and pose estimation of novel objects.
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object recognition have tended to process these modalities separately. We aim to bridge this divide by integrating images and point clouds on a unified transformer model. This approach integrates the modality-specific properties of images and point clouds and achieves fundamental downstream tasks in image and 3D object recognition on a unified transformer model by learning visual-geometric representations. In this work, we introduce Formula-Supervised Visual-Geometric Pre-training (FSVGP), a novel synthetic pre-training method that automatically generates aligned synthetic images and point clouds from mathematical formulas. Through cross-modality supervision, we enable supervised pre-training between visual and geometric modalities. FSVGP also reduces reliance on real data collection, cross-modality alignment, and human annotation. Our experimental results show that FSVGP pre-trains more effectively than VisualAtom and PC-FractalDB across six tasks: image and 3D object classification, detection, and segmentation. These achievements demonstrate FSVGP's superior generalization in image and 3D object recognition and underscore the potential of synthetic pre-training in visual-geometric representation learning. Our project website is available at https://ryosuke-yamada.github.io/fdsl-fsvgp/.
Over the past few years, the YOLO series of models has emerged as one of the dominant methodologies in the realm of object detection. Many studies have advanced these baseline models by modifying their architectures, enhancing data quality, and developing new loss functions. However, current models still exhibit deficiencies in processing feature maps, such as overlooking the fusion of cross-scale features and a static fusion approach that lacks the capability for dynamic feature adjustment. To address these issues, this paper introduces an efficient Fine-grained Multi-scale Dynamic Selection Module (FMDS Module), which applies a more effective dynamic feature selection and fusion method on fine-grained multi-scale feature maps, significantly enhancing the detection accuracy of small, medium, and large-sized targets in complex environments. Furthermore, this paper proposes an Adaptive Gated Multi-branch Focus Fusion Module (AGMF Module), which utilizes multiple parallel branches to perform complementary fusion of various features captured by the gated unit branch, FMDS Module branch, and TripletAttention branch. This approach further enhances the comprehensiveness, diversity, and integrity of feature fusion. This paper has integrated the FMDS Module, AGMF Module, into Yolov9 to develop a novel object detection model named FA-YOLO. Extensive experimental results show that under identical experimental conditions, FA-YOLO achieves an outstanding 66.1% mean Average Precision (mAP) on the PASCAL VOC 2007 dataset, representing 1.0% improvement over YOLOv9's 65.1%. Additionally, the detection accuracies of FA-YOLO for small, medium, and large targets are 44.1%, 54.6%, and 70.8%, respectively, showing improvements of 2.0%, 3.1%, and 0.9% compared to YOLOv9's 42.1%, 51.5%, and 69.9%.
As a social being, we have an intimate bond with the environment. A plethora of things in human life, such as lifestyle, health, and food are dependent on the environment and agriculture. It comes under our responsibility to support the environment as well as agriculture. However, traditional farming practices often result in inefficient resource use and environmental challenges. To address these issues, precision agriculture has emerged as a promising approach that leverages advanced technologies to optimise agricultural processes. In this work, a hybrid approach is proposed that combines the three different potential fields of model AI: object detection, large language model (LLM), and Retrieval-Augmented Generation (RAG). In this novel framework, we have tried to combine the vision and language models to work together to identify potential diseases in the tree leaf. This study introduces a novel AI-based precision agriculture system that uses Retrieval Augmented Generation (RAG) to provide context-aware diagnoses and natural language processing (NLP) and YOLOv8 for crop disease detection. The system aims to tackle major issues with large language models (LLMs), especially hallucinations and allows for adaptive treatment plans and real-time disease detection. The system provides an easy-to-use interface to the farmers, which they can use to detect the different diseases related to coffee leaves by just submitting the image of the affected leaf the model will detect the diseases as well as suggest potential remediation methodologies which aim to lower the use of pesticides, preserving livelihoods, and encouraging environmentally friendly methods. With an emphasis on scalability, dependability, and user-friendliness, the project intends to improve RAG-integrated object detection systems for wider agricultural applications in the future.
우리는 UrbanTwin Sim2Real LiDAR Challenge의 LUMPI 트랙에 대한 접근법을 기술한다. 이 트랙에서는 3D 객체 탐지기를 합성 데이터만으로 학습시켜 보지 못한 실제 노변 LiDAR 데이터로 평가하며, 동시에 합성 포인트 클라우드는 분포 사실성에 대해 점수가 매겨진다. 우리의 최종 제출물은 탐지 mAP 0.1333과 사실성 점수 0.9126으로 종합 0.4793점을 얻었다. 우리의 기여는 새로운 아키텍처가 아니다. PointPillars 기준 모델에서 출발하여 세 가지 원천에서 대부분의 이득을 얻었다. 첫째, 노변 LiDAR에서 작은 객체의 실패는 탐지 문제가 아니라 위치 추정 문제라는 진단이며, 이는 보행자 AP에서 상대 86퍼센트의 가치가 있는 매개변수 없는 기하학적 정제로 이어졌다. 둘째, 기본 제공되던 규칙이 유효한 예측을 파괴하고 있음을 밝혀낸 자체 후처리 감사이며, 이를 수정하여 Van 클래스에서 상대 335퍼센트라는 가장 큰 단일 탐지 이득을 얻었다. 셋째, 사실성 지표를 블랙박스가 아니라 해석적으로 다루어, 네 구성 요소 중 하나가 아홉 개 요약 통계량의 닫힌 형태 함수임을 보인 것이다. 또한 더 이전 가능한 결과라고 우리가 생각하는 실험 방법론도 보고한다. 평균 AP는 독립적인 클래스별 항으로 분해되므로 단일 제출이 서로 통제된 여러 실험을 담을 수 있고, 이전에 측정된 구성 요소만으로 조립한 제출물은 제출 전에 점수를 알 수 있다. 우리는 제출 전에 최종 점수를 소수점 넷째 자리까지 예측했다. 부정적 결과도 같은 분량으로 보고하며, 8절에서 제출된 점수에 기여한 모든 메커니즘에 대한 설명을 포함하여 데이터 출처와 규정 준수를 상세히 설명한다.
Two-stage detectors are state-of-the-art in object detection as well as pedestrian detection. However, the current two-stage detectors are inefficient as they do bounding box regression in multiple steps i.e. in region proposal networks and bounding box heads. Also, the anchor-based region proposal networks are computationally expensive to train. We propose F2DNet, a novel two-stage detection architecture which eliminates redundancy of current two-stage detectors by replacing the region proposal network with our focal detection network and bounding box head with our fast suppression head. We benchmark F2DNet on top pedestrian detection datasets, thoroughly compare it against the existing state-of-the-art detectors and conduct cross dataset evaluation to test the generalizability of our model to unseen data. Our F2DNet achieves 8.7\%, 2.2\%, and 6.1\% MR-2 on City Persons, Caltech Pedestrian, and Euro City Person datasets respectively when trained on a single dataset and reaches 20.4\% and 26.2\% MR-2 in heavy occlusion setting of Caltech Pedestrian and City Persons datasets when using progressive fine-tunning. Furthermore, F2DNet have significantly lesser inference time compared to the current state-of-the-art. Code and trained models will be available at https://github.com/AbdulHannanKhan/F2DNet.
Glass is very common in our daily life. Existing computer vision systems neglect it and thus may have severe consequences, e.g., a robot may crash into a glass wall. However, sensing the presence of glass is not straightforward. The key challenge is that arbitrary objects/scenes can appear behind the glass. In this paper, we propose an important problem of detecting glass surfaces from a single RGB image. To address this problem, we construct the first large-scale glass detection dataset (GDD) and propose a novel glass detection network, called GDNet-B, which explores abundant contextual cues in a large field-of-view via a novel large-field contextual feature integration (LCFI) module and integrates both high-level and low-level boundary features with a boundary feature enhancement (BFE) module. Extensive experiments demonstrate that our GDNet-B achieves satisfying glass detection results on the images within and beyond the GDD testing set. We further validate the effectiveness and generalization capability of our proposed GDNet-B by applying it to other vision tasks, including mirror segmentation and salient object detection. Finally, we show the potential applications of glass detection and discuss possible future research directions.
Fusing LiDAR point cloud features and image features in a homogeneous BEV space has been widely adopted for 3D object detection in autonomous driving. However, such methods are limited by the excessive compression of multi-modal features. While some works explore feature fusion in dense voxel spaces, they suffer from high computational costs and inefficiencies in query generation. To address these limitations, we propose a Dual-Domain Homogeneous Fusion network (DDHFusion), which leverages the complementary advantages of both BEV and voxel domains while mitigating their respective drawbacks. Specifically, we first transform image features into BEV and sparse voxel spaces using LSS and our proposed semantic-aware feature sampling module which can significantly reduces computational overhead by filtering unimportant voxels. For feature encoding, we design two networks for BEV and voxel feature fusion, incorporating novel cross-modal voxel and BEV Mamba blocks to resolve feature misalignment and enable efficient yet comprehensive scene perception. The output voxel features are injected into the BEV space to compensate for the loss of 3D details caused by height compression. For feature decoding, a progressive query generation module is implemented in the BEV domain to alleviate false negatives during query selection caused by feature compression and small object sizes. Finally, a progressive decoder can sequentially aggregate not only context-rich BEV features but also geometry-aware voxel features, ensuring more precise confidence prediction and bounding box regression. On the NuScenes dataset, DDHfusion achieves state-of-the-art performance, and further experiments demonstrate its superiority over other homogeneous fusion methods.
Recently, with the prevalence of large-scale image dataset, the co-occurrence information among classes becomes rich, calling for a new way to exploit it to facilitate inference. In this paper, we propose Obj-GloVe, a generic scene-based contextual embedding for common visual objects, where we adopt the word embedding method GloVe to exploit the co-occurrence between entities. We train the embedding on pre-processed Open Images V4 dataset and provide extensive visualization and analysis by dimensionality reduction and projecting the vectors along a specific semantic axis, and showcasing the nearest neighbors of the most common objects. Furthermore, we reveal the potential applications of Obj-GloVe on object detection and text-to-image synthesis, then verify its effectiveness on these two applications respectively.
Vehicle detection in remote sensing images has attracted increasing interest in recent years. However, its detection ability is limited due to lack of well-annotated samples, especially in densely crowded scenes. Furthermore, since a list of remotely sensed data sources is available, efficient exploitation of useful information from multi-source data for better vehicle detection is challenging. To solve the above issues, a multi-source active fine-tuning vehicle detection (Ms-AFt) framework is proposed, which integrates transfer learning, segmentation, and active classification into a unified framework for auto-labeling and detection. The proposed Ms-AFt employs a fine-tuning network to firstly generate a vehicle training set from an unlabeled dataset. To cope with the diversity of vehicle categories, a multi-source based segmentation branch is then designed to construct additional candidate object sets. The separation of high quality vehicles is realized by a designed attentive classifications network. Finally, all three branches are combined to achieve vehicle detection. Extensive experimental results conducted on two open ISPRS benchmark datasets, namely the Vaihingen village and Potsdam city datasets, demonstrate the superiority and effectiveness of the proposed Ms-AFt for vehicle detection. In addition, the generalization ability of Ms-AFt in dense remote sensing scenes is further verified on stereo aerial imagery of a large camping site.
엣지 비디오 분석 시스템은 실행 중에는 정답 레이블을 사용할 수 없으므로 로컬 탐지의 품질을 추정해야 한다. 탐지기는 보통 결과에 대한 신뢰도 점수를 제공하지만, 이러한 점수로는 놓친 모든 객체나 잘못 배치된 바운딩 박스를 드러낼 수 없다. 따라서 어떤 프레임에 잠재적 탐지 실패가 있어 클라우드의 더 강력한 모델로 넘겨야 하는지를 나타내는 판단 신호를 제공하는 품질 추정기가 필요하다. 신경망 기반 추정기는 이미 탐지를 수행 중인 GPU에 작업 부하를 더하는 반면, CPU 용량은 여유가 남아 있을 수 있다. 우리는 탐지 박스 이력을 압축하여 결정론적 결과 점수화를 지원함으로써 이 작업 부하를 CPU로 옮기는 예측 시간 일관성 IoU(Predictive Temporal Consistency IoU, PTC-IoU)를 제안한다. 대표적인 엣지 하드웨어인 Nvidia Jetson Orin Nano에서의 실험 결과, 신경망 방식과 비교하여 본 방법은 프레임당 추정기 지연 시간을 10.3 ms에서 2.2 ms로(4.7배 빠르게) 줄이고, 파이프라인 처리량을 13.6% 높였으며, 추정기 에너지 소비를 최대 95% 절감하면서도 여러 데이터셋에서 검증된 경쟁력 있는 최종 탐지 품질을 유지하였다.