PyTorchKR Papers

“Object Detection”

총 13,455편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2402.09781

A Comprehensive Review on Computer Vision Analysis of Aerial Data

With the emergence of new technologies in the field of airborne platforms and imaging sensors, aerial data analysis is becoming very popular, capitalizing on its advantages over land data. This paper presents a comprehensive review of the computer vision tasks within the domain of aerial data analysis. While addressing fundamental aspects such as object detection and tracking, the primary focus is on pivotal tasks like change detection, object segmentation, and scene-level analysis. The paper provides the comparison of various hyper parameters employed across diverse architectures and tasks. A substantial section is dedicated to an in-depth discussion on libraries, their categorization, and their relevance to different domain expertise. The paper encompasses aerial datasets, the architectural nuances adopted, and the evaluation metrics associated with all the tasks in aerial data analysis. Applications of computer vision tasks in aerial data across different domains are explored, with case studies providing further insights. The paper thoroughly examines the challenges inherent in aerial data analysis, offering practical solutions. Additionally, unresolved issues of significance are identified, paving the way for future research directions in the field of aerial data analysis.

arXiv:2609.27413v1cs.CV

S2A: 사전 정합 불필요 RGB-T 현저 객체 검출을 위한 의미-공간 정렬

S2A:Semantic-to-Spatial Alignment for Alignment-Free RGB-T Salient Object Detection

사전 정합 불필요 RGB-T 현저 객체 검출(RGB-T SOD)은 비용이 큰 사전 정합 없이 정합되지 않은 RGB 및 열화상 영상 쌍에서 현저 객체를 식별하는 것을 목표로 한다. 그러나 공간적 비정합은 픽셀 단위 대응을 깨뜨리고 교차 모달 융합 과정에서 특징 오염을 유발한다. 이 문제를 해결하기 위해, 우리는 사전 정합 불필요 RGB-T SOD를 위한 의미-공간 정렬 프레임워크인 S2A를 제안한다. 구체적으로, 전역 유도 계층적 융합 모듈(GGHF)이 먼저 전역 의미(semantic) 유도를 활용하여 배경 간섭을 억제하고 계층적 모달 내 특징을 정제한다. 이어서, 정합 불필요 교차 모달 채널 어텐션 모듈(AFCA)이 채널 단위 상호작용을 통해 상호 보완적 의미 정보를 전역적으로 교환하여, 국소 공간 비정합으로 인한 간섭을 효과적으로 극복한다. 마지막으로, 공간 변형 가능 교차 어텐션 모듈(SDCA)이 적응형 샘플링 오프셋을 예측하여 국소 교차 모달 공간 대응을 복원한다. 이러한 의미-공간 패러다임을 통해 S2A는 먼저 신뢰할 수 있는 교차 모달 의미 상호작용을 가능하게 한 뒤 국소 공간 보정을 수행하여, 비정합으로 인한 특징 오염을 효과적으로 줄인다. 불필요한 부가 기법 없이 S2A는 여러 공개 사전 정합 불필요 RGB-T 벤치마크에서 매우 경쟁력 있는 성능을 달성하며, 비정합 유발 특징 오염 완화에서의 효과를 보여준다.

arXiv:1707.07381

Group-wise Deep Co-saliency Detection

In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output. The proposed approach captures the group-wise interaction information for group images by learning a semantics-aware image representation based on a convolutional neural network, which adaptively learns the group-wise features for co-saliency detection. Furthermore, the proposed approach discovers the collaborative and interactive relationships between group-wise feature representation and single-image individual feature representation, and model this in a collaborative learning framework. Finally, we set up a unified end-to-end deep learning scheme to jointly optimize the process of group-wise feature representation learning and the collaborative learning, leading to more reliable and robust co-saliency detection results. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.

arXiv:2407.00906

GSO-YOLO: Global Stability Optimization YOLO for Construction Site Detection

Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of artificial intelligence, particularly in the field of computer vision, the automation of safety monitoring on construction sites has emerged as a solution to this longstanding issue. Despite achieving impressive performance, advanced object detection methods like YOLOv8 still face challenges in handling the complex conditions found at construction sites. To solve these problems, this study presents the Global Stability Optimization YOLO (GSO-YOLO) model to address challenges in complex construction sites. The model integrates the Global Optimization Module (GOM) and Steady Capture Module (SCM) to enhance global contextual information capture and detection stability. The innovative AIoU loss function, which combines CIoU and EIoU, improves detection accuracy and efficiency. Experiments on datasets like SODA, MOCS, and CIS show that GSO-YOLO outperforms existing methods, achieving SOTA performance.

arXiv:2409.13688v2cs.CV

심층 학습을 통한 소비재 유래 미세플라스틱 및 나노플라스틱의 형태학적 검출 및 분류

Morphological Detection and Classification of Microplastics and Nanoplastics Emerged from Consumer Products by Deep Learning

플라스틱 오염은 건강과 환경 시스템에 영향을 미치며 점차 심각해지는 글로벌 문제로, 음용수부터 공기까지 다양한 매체에서 미세플라스틱과 나노플라스틱이 발견되고 있습니다. 이러한 오염물질을 연구하는 전통적인 방식은 노동 집약적이고 많은 시간이 소요되어, 보다 효율적인 기술로의 전환이 요구됩니다. 이에 대응하여 본 논문에서는 객체 검출(object detection) 알고리즘을 활용해 미세 및 나노플라스틱을 자동으로 검출하고 분류하도록 설계된 새로운 오픈소스 데이터셋인 MiNa(micro- and nanoplastics)를 소개합니다. 현실적인 수생 조건을 시뮬레이션한 주사전자현미경(SEM) 이미지로 구성된 이 데이터셋은 넓은 크기 스펙트럼에 걸쳐 플라스틱을 폴리머 유형별로 분류합니다. 우리는 MiNa에 최첨단(SOTA) 검출 알고리즘을 적용하여 그 효과를 평가하고, 각 방법의 고유한 과제와 잠재력을 규명합니다. 이 데이터셋은 미세플라스틱 연구에 사용할 수 있는 자원의 중요한 공백을 메울 뿐만 아니라, 향후 해당 분야의 발전을 위한 탄탄한 기반을 제공합니다.

arXiv:1903.02827

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up

Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks trained with image level labels only tend to focus on the most discriminative parts while missing other object parts, which could provide complementary information. In this paper, we approach this problem from a different perspective. We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks. Given image level labels only, we first extract rough object instances by performing weakly supervised object detection and instance segmentation using Mask R-CNN and CRF-based segmentation. Then we estimate and search for the best parts model for each object instance under the principle of preserving as much diversity as possible. In the last stage, we build a bi-directional long short-term memory (LSTM) network to fuze and encode the partial information of these complementary parts into a comprehensive feature for image classification. Experimental results indicate that the proposed method not only achieves significant improvement over our baseline models, but also outperforms state-of-the-art algorithms by a large margin (6.7%, 2.8%, 5.2% respectively) on Stanford Dogs 120, Caltech-UCSD Birds 2011-200 and Caltech 256.

arXiv:2606.29963v1cs.CV

설명 가능성 인식 프러스텀 공격: LiDAR 기반 3D 객체 검출기의 구조적 취약점 노출

Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors

포인트 클라우드 기반 3D 객체 검출기의 구조적 취약점은 아직 충분히 이해되지 않고 있다. 기존 연구는 주로 독립적인 3D 객체 모델에 대한 적대적 강건성을 연구하였으며, 최근의 LiDAR 스푸핑 공격은 보다 풍부하고 현실적인 주행 장면을 대상으로 하지만 검출기 동작 이해나 공격 효율성보다는 물리적 실현 가능성에 초점을 맞추고 있다. 본 연구에서는 LiDAR 기반 검출기가 복잡한 장면에서 공간적 증거에 어떻게 의존하는지, 그리고 이러한 의존 패턴이 더 효율적으로 실패를 유도하는 데 활용될 수 있는지를 조사한다. 이를 위해 설명 가능성 기반 적대적 분석 방법론을 제안한다. 우리는 장면 전반에 걸쳐 Integrated Gradient 어트리뷰션을 집계하여 LiDAR 기반 3D 객체 검출기를 위한 범용 살리언시 맵을 생성하는 Saliency-LiDAR(SALL) 방법을 소개한다. 이 맵의 안내를 받아, 전체 객체 영역을 균일하게 공격하는 대신 가장 영향력 있는 프러스텀만을 선택적으로 교란하는 설명 가능성 인식 프러스텀 공격(EFA)을 설계한다. KITTI와 nuScenes에서 PointPillars 및 SECOND 등의 검출기를 대상으로 한 실험 결과, EFA는 최신 비살리언시 인식 기준선 대비 25~50% 더 적은 교란 프러스텀으로 검출 재현율을 15 퍼센트포인트 이상 감소시키는 것으로 나타났다. 이러한 결과는 현대 3D 검출기가 소수의 공간 영역에 판별적 증거를 집중시키고 있음을 드러내며, 현재 LiDAR 인식 시스템의 구조적 강건성 취약점을 노출한다. 코드는 https://github.com/SecMindLab/Saliency_LiDAR 에서 공개되어 있다.

arXiv:1912.05846공식 코드 · Papers with Code

The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images

A correct localisation of tables in a document is instrumental for determining their structure and extracting their contents; therefore, table detection is a key step in table understanding. Nowadays, the most successful methods for table detection in document images employ deep learning algorithms; and, particularly, a technique known as fine-tuning. In this context, such a technique exports the knowledge acquired to detect objects in natural images to detect tables in document images. However, there is only a vague relation between natural and document images, and fine-tuning works better when there is a close relation between the source and target task. In this paper, we show that it is more beneficial to employ fine-tuning from a closer domain. To this aim, we train different object detection algorithms (namely, Mask R-CNN, RetinaNet, SSD and YOLO) using the TableBank dataset (a dataset of images of academic documents designed for table detection and recognition), and fine-tune them for several heterogeneous table detection datasets. Using this approach, we considerably improve the accuracy of the detection models fine-tuned from natural images (in mean a 17%, and, in the best case, up to a 60%).

arXiv:2408.16923

Analyzing Errors in Controlled Turret System Given Target Location Input from Artificial Intelligence Methods in Automatic Target Recognition

In this paper, we assess the movement error of a targeting system given target location data from artificial intelligence (AI) methods in automatic target recognition (ATR) systems. Few studies evaluate the impacts on the accuracy in moving a targeting system to an aimpoint provided in this manner. To address this knowledge gap, we assess the performance of a controlled gun turret system given target location from an object detector developed from AI methods. In our assessment, we define a measure of object detector error and examine the correlations with several standard metrics in object detection. We then statistically analyze the object detector error data and turret movement error data acquired from controlled targeting simulations, as well as their aggregate error, to examine the impact on turret movement accuracy. Finally, we study the correlations between additional metrics and the probability of a hit. The results indicate that AI technologies are a significant source of error to targeting systems. Moreover, the results suggest that metrics such as the confidence score, intersection-over-union, average precision and average recall are predictors of accuracy against stationary targets with our system parameters.

arXiv:2603.05384v2cs.CV

ORMOT: 전방향 지시 다중 객체 추적을 위한 데이터셋 및 프레임워크

ORMOT: A Dataset and Framework for Omnidirectional Referring Multi-Object Tracking

전방향 카메라는 360° 공간 커버리지를 제공하여 자율 주행 및 비디오 감시와 같은 응용에서 점점 더 중요해지고 있다. 다중 객체 추적(MOT)과 그 언어 유도 확장인 지시 다중 객체 추적(RMOT)은 주목할 만한 진전을 이루었지만, 기존 방법은 시야가 제한된 일반 카메라에 의존하여 대상이 프레임 밖으로 이동할 때 중요한 문맥 단서가 손실된다. 이는 순차적 행동, 공간 관계, 집단 행동을 포함하는 장기 언어 설명을 해석하는 모델의 능력을 근본적으로 제한한다. 본 연구에서는 RMOT을 전방향 영상으로 확장하는 새로운 과제인 전방향 지시 다중 객체 추적(ORMOT)을 제안한다. 360° 커버리지는 정확한 언어 유도 추적을 위해 완전한 장면 문맥을 보장한다. 이 과제를 발전시키기 위해 27개의 전방향 장면, 848개의 언어 설명, 3,401개의 주석 객체로 구성된 데이터셋 ORSet을 구축한다. 또한 복잡한 360° 환경에서 제로샷 언어 유도 검출과 견고한 프레임 간 연관(association)을 가능하게 하는 LVLM 기반 프레임워크 ORTrack을 제안한다. ORSet에 대한 실험은 ORTrack이 최신 최고(state-of-the-art) 성능을 달성함을 보여주며, 향후 연구를 위한 강한 기준선을 제공한다. 데이터셋과 코드는 https://github.com/chen-si-jia/ORMOT 에서 오픈 소스로 공개될 예정이다.

arXiv:2208.11122공식 코드 · Papers with Code

Distance-Aware Occlusion Detection with Focused Attention

For humans, understanding the relationships between objects using visual signals is intuitive. For artificial intelligence, however, this task remains challenging. Researchers have made significant progress studying semantic relationship detection, such as human-object interaction detection and visual relationship detection. We take the study of visual relationships a step further from semantic to geometric. In specific, we predict relative occlusion and relative distance relationships. However, detecting these relationships from a single image is challenging. Enforcing focused attention to task-specific regions plays a critical role in successfully detecting these relationships. In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection. Specifically, our model increases the distance F1-score from 33.8% to 38.6% and boosts the occlusion F1-score from 34.4% to 41.2%. Our code is publicly available.

arXiv:2404.01727공식 코드 · Papers with Code

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge

We focus on the generalization ability of the 6-DoF grasp detection method in this paper. While learning-based grasp detection methods can predict grasp poses for unseen objects using the grasp distribution learned from the training set, they often exhibit a significant performance drop when encountering objects with diverse shapes and structures. To enhance the grasp detection methods' generalization ability, we incorporate domain prior knowledge of robotic grasping, enabling better adaptation to objects with significant shape and structure differences. More specifically, we employ the physical constraint regularization during the training phase to guide the model towards predicting grasps that comply with the physical rule on grasping. For the unstable grasp poses predicted on novel objects, we design a contact-score joint optimization using the projection contact map to refine these poses in cluttered scenarios. Extensive experiments conducted on the GraspNet-1billion benchmark demonstrate a substantial performance gain on the novel object set and the real-world grasping experiments also demonstrate the effectiveness of our generalizing 6-DoF grasp detection method.

arXiv:2404.03539공식 코드 · Papers with Code

Is CLIP the main roadblock for fine-grained open-world perception?

Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving, which require the ability to respond to open-world stimuli. A key ingredient is the ability to identify objects based on free-form textual queries defined at inference time - a task known as open-vocabulary object detection. Multimodal backbones like CLIP are the main enabling technology for current open-world perception solutions. Despite performing well on generic queries, recent studies highlighted limitations on the fine-grained recognition capabilities in open-vocabulary settings - i.e., for distinguishing subtle object features like color, shape, and material. In this paper, we perform a detailed examination of these open-vocabulary object recognition limitations to find the root cause. We evaluate the performance of CLIP, the most commonly used vision-language backbone, against a fine-grained object-matching benchmark, revealing interesting analogies between the limitations of open-vocabulary object detectors and their backbones. Experiments suggest that the lack of fine-grained understanding is caused by the poor separability of object characteristics in the CLIP latent space. Therefore, we try to understand whether fine-grained knowledge is present in CLIP embeddings but not exploited at inference time due, for example, to the unsuitability of the cosine similarity matching function, which may discard important object characteristics. Our preliminary experiments show that simple CLIP latent-space re-projections help separate fine-grained concepts, paving the way towards the development of backbones inherently able to process fine-grained details. The code for reproducing these experiments is available at https://github.com/lorebianchi98/FG-CLIP.

arXiv:1411.2861

Computational Baby Learning

Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition capability can be gradually further improved by exploring and/or interacting with the real instances in the physical world. Inspired by these observations, we propose a computational model for slightly-supervised object detection, based on prior knowledge modelling, exemplar learning and learning with video contexts. The prior knowledge is modeled with a pre-trained Convolutional Neural Network (CNN). When very few instances of a new concept are given, an initial concept detector is built by exemplar learning over the deep features from the pre-trained CNN. Simulating the baby's interaction with physical world, the well-designed tracking solution is then used to discover more diverse instances from the massive online unlabeled videos. Once a positive instance is detected/identified with high score in each video, more variable instances possibly from different view-angles and/or different distances are tracked and accumulated. Then the concept detector can be fine-tuned based on these new instances. This process can be repeated again and again till we obtain a very mature concept detector. Extensive experiments on Pascal VOC-07/10/12 object detection datasets well demonstrate the effectiveness of our framework. It can beat the state-of-the-art full-training based performances by learning from very few samples for each object category, along with about 20,000 unlabeled videos.

arXiv:2204.05072

Few-Shot Object Detection in Unseen Domains

Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples of novel classes and test-time data belong to the same domain. However, this assumption does not hold in various industrial and robotics applications, where a model can learn novel classes from a source domain while inferring on classes from a target domain. In this work, we address the task of zero-shot domain adaptation, also known as domain generalization, for FSOD. Specifically, we assume that neither images nor labels of the novel classes in the target domain are available during training. Our approach for solving the domain gap is two-fold. First, we leverage a meta-training paradigm, where we learn the domain shift on the base classes, then transfer the domain knowledge to the novel classes. Second, we propose various data augmentations techniques on the few shots of novel classes to account for all possible domain-specific information. To constraint the network into encoding domain-agnostic class-specific representations only, a contrastive loss is proposed to maximize the mutual information between foreground proposals and class embeddings and reduce the network's bias to the background information from target domain. Our experiments on the T-LESS, PASCAL-VOC, and ExDark datasets show that the proposed approach succeeds in alleviating the domain gap considerably without utilizing labels or images of novel categories from the target domain.

arXiv:2205.03381

MINI: Mining Implicit Novel Instances for Few-Shot Object Detection

Learning from a few training samples is a desirable ability of an object detector, inspiring the explorations of Few-Shot Object Detection (FSOD). Most existing approaches employ a pretrain-transfer paradigm. The model is first pre-trained on base classes with abundant data and then transferred to novel classes with a few annotated samples. Despite the substantial progress, the FSOD performance is still far behind satisfactory. During pre-training, due to the co-occurrence between base and novel classes, the model is learned to treat the co-occurred novel classes as backgrounds. During transferring, given scarce samples of novel classes, the model suffers from learning discriminative features to distinguish novel instances from backgrounds and base classes. To overcome the obstacles, we propose a novel framework, Mining Implicit Novel Instances (MINI), to mine the implicit novel instances as auxiliary training samples, which widely exist in abundant base data but are not annotated. MINI comprises an offline mining mechanism and an online mining mechanism. The offline mining mechanism leverages a self-supervised discriminative model to collaboratively mine implicit novel instances with a trained FSOD network. Taking the mined novel instances as auxiliary training samples, the online mining mechanism takes a teacher-student framework to simultaneously update the FSOD network and the mined implicit novel instances on the fly. Extensive experiments on PASCAL VOC and MS-COCO datasets show MINI achieves new state-of-the-art performance on any shot and split. The significant performance improvements demonstrate the superiority of our method.

arXiv:2303.02998

Pseudo-label Correction and Learning For Semi-Supervised Object Detection

Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances effectively alleviate the classification noise in SSOD, while the localization noise which is a non-negligible part of SSOD is not well-addressed. In this paper, we analyse the localization noise from the generation and learning phases, and propose two strategies, namely pseudo-label correction and noise-unaware learning. For pseudo-label correction, we introduce a multi-round refining method and a multi-vote weighting method. The former iteratively refines the pseudo boxes to improve the stability of predictions, while the latter smoothly self-corrects pseudo boxes by weighing the scores of surrounding jittered boxes. For noise-unaware learning, we introduce a loss weight function that is negatively correlated with the Intersection over Union (IoU) in the regression task, which pulls the predicted boxes closer to the object and improves localization accuracy. Our proposed method, Pseudo-label Correction and Learning (PCL), is extensively evaluated on the MS COCO and PASCAL VOC benchmarks. On MS COCO, PCL outperforms the supervised baseline by 12.16, 12.11, and 9.57 mAP and the recent SOTA (SoftTeacher) by 3.90, 2.54, and 2.43 mAP under 1\%, 5\%, and 10\% labeling ratios, respectively. On PASCAL VOC, PCL improves the supervised baseline by 5.64 mAP and the recent SOTA (Unbiased Teacherv2) by 1.04 mAP on AP$^{50}$.

arXiv:2108.08162공식 코드 · Papers with Code

Specificity-preserving RGB-D Saliency Detection

Salient object detection (SOD) on RGB and depth images has attracted more and more research interests, due to its effectiveness and the fact that depth cues can now be conveniently captured. Existing RGB-D SOD models usually adopt different fusion strategies to learn a shared representation from the two modalities (\ie, RGB and depth), while few methods explicitly consider how to preserve modality-specific characteristics. In this study, we propose a novel framework, termed SPNet} (Specificity-preserving network), which benefits SOD performance by exploring both the shared information and modality-specific properties (\eg, specificity). Specifically, we propose to adopt two modality-specific networks and a shared learning network to generate individual and shared saliency prediction maps, respectively. To effectively fuse cross-modal features in the shared learning network, we propose a cross-enhanced integration module (CIM) and then propagate the fused feature to the next layer for integrating cross-level information. Moreover, to capture rich complementary multi-modal information for boosting the SOD performance, we propose a multi-modal feature aggregation (MFA) module to integrate the modality-specific features from each individual decoder into the shared decoder. By using a skip connection, the hierarchical features between the encoder and decoder layers can be fully combined. Extensive experiments demonstrate that our~\ours~outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection benchmarks. The project is publicly available at: https://github.com/taozh2017/SPNet.

arXiv:2301.06679

Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff

Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspires us to rethink saliency detection to achieve a favorable balance between efficiency and accuracy. To this end, we design a lightweight framework while maintaining satisfying competitive accuracy. Specifically, we propose a novel trilateral decoder framework by decoupling the U-shape structure into three complementary branches, which are devised to confront the dilution of semantic context, loss of spatial structure and absence of boundary detail, respectively. Along with the fusion of three branches, the coarse segmentation results are gradually refined in structure details and boundary quality. Without adding additional learnable parameters, we further propose Scale-Adaptive Pooling Module to obtain multi-scale receptive filed. In particular, on the premise of inheriting this framework, we rethink the relationship among accuracy, parameters and speed via network depth-width tradeoff. With these insightful considerations, we comprehensively design shallower and narrower models to explore the maximum potential of lightweight SOD. Our models are purposed for different application environments: 1) a tiny version CTD-S (1.7M, 125FPS) for resource constrained devices, 2) a fast version CTD-M (12.6M, 158FPS) for speed-demanding scenarios, 3) a standard version CTD-L (26.5M, 84FPS) for high-performance platforms. Extensive experiments validate the superiority of our method, which achieves better efficiency-accuracy balance across five benchmarks.

arXiv:1706.03309

Bicycle Detection Based On Multi-feature and Multi-frame Fusion in low-resolution traffic videos

As a major type of transportation equipments, bicycles, including electrical bicycles, are distributed almost everywhere in China. The accidents caused by bicycles have become a serious threat to the public safety. So bicycle detection is one major task of traffic video surveillance systems in China. In this paper, a method based on multi-feature and multi-frame fusion is presented for bicycle detection in low-resolution traffic videos. It first extracts some geometric features of objects from each frame image, then concatenate multiple features into a feature vector and use linear support vector machine (SVM) to learn a classifier, or put these features into a cascade classifier, to yield a preliminary detection result regarding whether an object is a bicycle. It further fuses these preliminary detection results from multiple frames to provide a more reliable detection decision, together with a confidence level of that decision. Experimental results show that this method based on multi-feature and multi-frame fusion can identify bicycles with high accuracy and low computational complexity. It is, therefore, applicable for real-time traffic video surveillance systems.