共查询到20条相似文献，搜索用时 15 毫秒
1.
Philipp Lottes Jens Behley Nived Chebrolu Andres Milioto Cyrill Stachniss 《野外机器人技术杂志》2020,37(1):20-34
Conventional farming still relies on large quantities of agrochemicals for weed management which have several negative side‐effects on the environment. Autonomous robots offer the potential to reduce the amount of chemicals applied, as robots can monitor and treat each plant in the field individually and thereby circumventing the uniform chemical treatment of the whole field. Such agricultural robots need the ability to identify individual crops and weeds in the field using sensor data and must additionally select effective treatment methods based on the type of weed. For example, certain types of weeds can only be effectively treated mechanically due to their resistance to herbicides, whereas other types can be treated trough selective spraying. In this article, we present a novel system that provides the necessary information for effective plant‐specific treatment. It estimates the stem location for weeds, which enables the robots to perform precise mechanical treatment, and at the same time provides the pixel‐accurate area covered by weeds for treatment through selective spraying. The major challenge in developing such a system is the large variability in the visual appearance that occurs in different fields. Thus, an effective classification system has to robustly handle substantial environmental changes including varying weed pressure, various weed types, different growth stages, changing visual appearance of the plants and the soil. Our approach uses an end‐to‐end trainable fully convolutional network that simultaneously estimates plant stem positions as well as the spatial extent of crop plants and weeds. It jointly learns how to detect the stems and the pixel‐wise semantic segmentation and incorporates spatial information by considering image sequences of local field strips. The jointly learned feature representation for both tasks furthermore exploits the crop arrangement information that is often present in crop fields. This information is considered even if it is only observable from the image sequences and not a single image. Such image sequences, as typically provided by robots navigating over the field along crop rows, enable our approach to robustly estimate the semantic segmentation and stem positions despite the large variations encountered in different fields. We implemented and thoroughly tested our approach on images from multiple farms in different countries. The experiments show that our system generalizes well to previously unseen fields under varying environmental conditions—a key capability to deploy such systems in the real world. Compared to state‐of‐the‐art approaches, our approach generalizes well to unseen fields and not only substantially improves the stem detection accuracy, that is, distinguishing crop and weed stems, but also improves the semantic segmentation performance. 相似文献
2.
3.
类别级物体识别与检测属于计算机视觉领域的一个基础性问题,主要研究在图像或视频流中识别和定位出其中感兴趣的物体.在基于小规模数据集的类别级物体识别与检测应用中,模型过拟合、类不平衡和跨领域时特征分布变化等关键问题与挑战交织在一起.本文介绍了迁移学习理论的研究现状,对迁移学习理论解决基于小规模数据集的物体识别与检测中遇到的主要问题的研究思路和前沿技术进行了着重论述和分析.最后对该领域的研究重点和技术发展趋势进行了探讨. 相似文献
4.
Agricultural robots rely on semantic segmentation for distinguishing between crops and weeds to perform selective treatments and increase yield and crop health while reducing the amount of chemicals used. Deep‐learning approaches have recently achieved both excellent classification performance and real‐time execution. However, these techniques also rely on a large amount of training data, requiring a substantial labeling effort, both of which are scarce in precision agriculture. Additional design efforts are required to achieve commercially viable performance levels under varying environmental conditions and crop growth stages. In this paper, we explore the role of knowledge transfer between deep‐learning‐based classifiers for different crop types, with the goal of reducing the retraining time and labeling efforts required for a new crop. We examine the classification performance on three datasets with different crop types and containing a variety of weeds and compare the performance and retraining efforts required when using data labeled at pixel level with partially labeled data obtained through a less time‐consuming procedure of annotating the segmentation output. We show that transfer learning between different crop types is possible and reduces training times for up to 80%. Furthermore, we show that even when the data used for retraining are imperfectly annotated, the classification performance is within 2% of that of networks trained with laboriously annotated pixel‐precision data. 相似文献
5.
针对高速公路场景下的车辆目标检测问题,提出了一种改进的YOLOv4网络对交通场景下车辆目标进行检测的方法;制作了一个多天候、多时段、多场景的车辆目标数据集,并依据数据集得到检测模型;提出多标签检测方法,并在多标签之间建立约束关系,得到更完善的车辆信息;提出了一个图像拼接检测方法,将多幅图像通过拼接层连接后进行车辆检测,... 相似文献
6.
针对关键岗位的人员行为分析的问题,提出了一种基于视频的行为分析方法。制作了包含多姿态样本的岗位人员行为数据集,并使用YOLOv3网络训练该数据集得到行为检测模型。使用提出的人员行为分析算法结合行为检测模型对视频进行处理,对人员行为进行初步分析。在人员行为分析算法的基础上,结合图像相似度和明暗度等特征,进行深度分析并给出离岗、睡觉和玩手机事件的判断结果。实验结果表明,制作的数据集在人员行为检测中有较高的检测精度,同时行为分析的准确度也较高,并且能够进行实时处理。 相似文献
7.
Yonglin Tian Xuan Li Kunfeng Wang Fei-Yue Wang 《IEEE/CAA Journal of Automatica Sinica》2018,5(2):539-546
In the area of computer vision, deep learning has produced a variety of state-of-the-art models that rely on massive labeled data. However, collecting and annotating images from the real world is too demanding in terms of labor and money investments, and is usually inflexible to build datasets with specific characteristics, such as small area of objects and high occlusion level. Under the framework of Parallel Vision, this paper presents a purposeful way to design artificial scenes and automatically generate virtual images with precise annotations. A virtual dataset named ParallelEye is built, which can be used for several computer vision tasks. Then, by training the DPM (Deformable parts model) and Faster R-CNN detectors, we prove that the performance of models can be significantly improved by combining ParallelEye with publicly available real-world datasets during the training phase. In addition, we investigate the potential of testing the trained models from a specific aspect using intentionally designed virtual datasets, in order to discover the flaws of trained models. From the experimental results, we conclude that our virtual dataset is viable to train and test the object detectors. 相似文献
8.
近年来,深度学习算法逐渐尝试应用于目标检测领域。本文针对实际交通场景下的车辆目标,应用深度学习目标分类算法中具有代表性的Faster R-CNN框架,结合ImageNet中的车辆数据集,把场景中的目标检测问题转化为目标的二分类问题,进行车辆目标的检测识别。相比传统机器学习目标检测算法,基于深度学习的目标检测算法在检测准确度和执行效率上优势明显。通过本实验结果分析表明,该方法在识别精度以及速度上均取得了显著的提高。 相似文献
9.
舰船目标检测是海域监控、港口流量统计、舰船身份识别以及行为分析与取证等智能海事应用的基石。随着我国海洋强国建设的推进,智慧航运和智慧海洋工程迅速发展,对通过海事监控视频开展有效的舰船目标检测识别以确保航运和海洋工程安全的需求日益紧迫。本文针对基于海事监控视频的舰船目标检测任务,回顾了舰船目标检测数据集及性能评价指标、基于传统机器学习和基于卷积神经网络的深度学习的目标检测方法等方面的国内外研究现状,分析了海洋环境中舰船目标检测任务面临的舰船目标尺度的多样性、舰船类别的多样性、海洋气象的复杂性、水面的动态性、相机的运动性和图像的低质量等技术难点,并通过实验验证,在多尺度特征融合、数据增广和能耗降低等方面提出了舰船目标检测的优化方法;同时,结合前人研究指出舰船目标检测数据集的发展应关注分类粒度的适宜性、标注的一致性和数据集的易扩充性,应加强对多尺度目标（尤其是小型目标）检测的模型结构的研究,为进一步提升舰船目标检测任务的综合性能,促进舰船目标检测技术的应用提供了新的思路。 相似文献
10.
抓取是机器人在服务与工业领域中进行人机协调的重要能力,得到一个准确的抓取检测结果是机械臂能否完成抓取任务的关键.为了提高抓取检测的准确率以及实时性,提出了一种由CenterNet改进的基于关键点估计的抓取检测算法.在网络的特征提取层使用了特征融合方法融合不同的特征图,减少特征的丢失;增加了角度预测分支用来预测抓取角度;... 相似文献
11.
目标检测技术是光学遥感图像理解的基础问题, 具有重要的应用价值. 本文对遥感图像目标检测算法发展进行了梳理和分析. 首先阐述了遥感图像目标检测的特点和挑战; 之后系统总结了典型的检测方法, 包括早期的基于手工设计特征的算法和现阶段基于深度学习的方法, 对于深度学习方法首先介绍了典型的目标检测模型, 进而针对遥感图像本身的难点详细梳理了优化改进方案; 接着介绍了常用的检测数据集, 并对现有方法的性能进行比较; 最后对现阶段问题进行总结并对未来发展趋势进行展望. 相似文献
12.
针对图像标注中疲劳、粗心等因素引起的标签遗漏现象,使得模型训练时难以正确区分正负样本,进而影响模型性能.设计了一种协同修正技术,通过多次迭代更新训练集,将潜在无标签的目标进行对象擦除,降低训练集的错误监督信息,避免人工的重复检查和重复标注.该方法无需进行算法参数调整、不依赖具体网络结构,低成本地减少数据集错误从而提升模型训练精度.在YOLOv5算法的实验基础上表明协同修正操作仅迭代1次即有明显的改善效果,并在多个公共数据集上能够提升0.4%～1.4%的检测精度,当数据集中的标签遗漏率达到40%时依然能够生效.该方法对数据集中样本的数据量和类别数没有限制,可应用于电商、遥感、通用等多种目标检测场景,保持着较好的鲁棒性和泛化性. 相似文献
13.
针对目标检测网络单阶改进目标检测器（RefineDet）对类间不平衡数据集中小样本类别检测性能差的问题,提出一种部分加权损失函数SWLoss。首先,以每个训练批量中不同类别样本数量的倒数作为启发式的类间样本平衡因子,对分类损失中的不同类别进行加权,从而提高对小样本类别学习的关注程度;然后引入多任务平衡因子对分类损失和回归损失进行加权,缩小两个任务学习速率的差异;最后,在目标类别样本数量存在大幅差异的Pascal VOC 2007数据集和点阵字符数据集上进行实验。结果表明,与原始RefineDet相比,基于SWLoss的RefineDet明显提高了小样本类别的检测精度,它在两个数据集上的平均精度均值（mAP）分别提高了1.01、9.86个百分点;与基于损失平衡函数和加权成对损失的RefineDet相比,基于SWLoss的RefineDet在两个数据集上的mAP分别提高了0.68、4.73和0.49、1.48个百分点。 相似文献
14.
现有目标检测算法主要以图像中的大目标作为研究对象,针对小目标的研究比较少且存在检测精确度低、无法满足实时性要求的问题,基于此,提出一种基于深度学习目标检测框架PVANet的实时小目标检测方法。首先,构建一个专用于小目标检测的基准数据集,它包含的目标在一幅图像中的占比非常小且存在截断、遮挡等干扰,可以更好地评估小目标检测方法的优劣;其次,结合区域建议网络(RPN)提出一种生成高质量小目标候选框的方法以提高算法的检测精确度和速度;选用step和inv两种新的学习率策略以改善模型性能,进一步提升检测精确度。在构建的小目标数据集上,相比原PVANet算法平均检测精确度提高了10. 67%,速度提升了约30%。实验结果表明,该方法是一个有效的小目标检测算法,达到了实时检测的效果。 相似文献
15.
A multiclass 3D object recognition has perceived a numerous evolution with respect to both accuracy and speed. This study introduces the implementation of modern YOLO algorithms (YOLOv3, YOLOv4, and YOLOv5) for multiclass 3D object detection and recognition. All YOLO algorithms have been tested according to a very large scaled dataset (Pascal VOC dataset). Performance evaluation has targeted the calculation of the following metrics; mAP (mean average precision), recall, F1-score, IOU (intersection over union), and the running time. Experimental results demonstrate that the YOLOv3 has targeted mAP of 77%, IOU of 0.41 and the total running time was almost 8 h. Moreover, in YOLOv4, it has targeted mAP of 55%, IOU of 0.035 and the total running time nearly 7 h. In addition, YOLOv5 has established the mAP of 48%, IOU of 0.045, and the total running time was about 3 h. Finally, a modified version of YOLOv5 has been proposed in the state-of-the-art of optimizing its hyperparameters and layering system. Accordingly, the mAP scored about 55% with 3 h running time. The final conclusions of this study have demonstrated that YOLOv3 has scored the highest recognition accuracy, however, the proposed modified YOLOv5 has scored the least processing time. 相似文献
16.
随着移动设备与社交网络的迅速发展,数字图像的数据规模急剧增加,图像目标类别检测已经发展成为目前计算机视觉领域内的一个研究热点。对图像目标类别检测的关键问题进行了综述。首先对目标类别检测的研究背景进行了介绍;然后对目标类别检测技术进行了综述,其中包括外观模型、分类器和定位策略3个核心技术,以及数据集和评价标准;最后列出了目前目标类别检测算法的测试结果,并总结了目标类别检测的主要研究难点和发展方向。 相似文献
17.
目的 有丝分裂细胞核计数是乳腺癌诊断和组织学分级的3个重要评分指标之一,基于深度学习的自动检测方法,可以有效辅助医生进行乳腺病理图像有丝分裂细胞核识别和计数。而当前研究中的公开数据集多为竞赛所用,由举办方联合数据提供者挑选而来,与医院临床应用中所使用的数据存在较大的差异,不利于模型性能及泛化能力的测试验证。针对以上问题,本文发布了来自中国赣州市立医院临床环境的数据集GZMH （Ganzhou municipal hospital）。方法 整理并公开发布的数据集GZMH包含55幅全视野数字切片（whole slide images,WSIs）临床乳腺癌病理图像,提供了用于有丝分裂细胞核目标检测和语义分割研究的两种标注,并由2名高年资医师对3名初级病理医师的标注进行了复核。5种主流目标检测方法和5种经典分割方法在GZMH数据集上进行了训练和测试,检验它们在临床数据集GZMH上的性能。结果 目标检测方法实验结果比较中,SSD （single shot multibox detector）模型取得了最佳的效果,F1分数为0.511;分割方法实验结果比较中,R2U-Net （recurrent rsidual convolutional neural network based on U-Net）性能最佳,F1分数为0.430。所有方法在面对较大规模的临床数据集GZMH时体现的性能都明显低于它们在一些公开数据集上的性能。结论 本文所提出的GZMH数据集能够用于有丝分裂目标检测与语义分割研究任务,且此数据集中的图像更加接近实际的应用场景,在推动乳腺病理图像有丝分裂细胞核分割的研究和临床应用方面具有较大的价值。数据集的在线发布地址为：https：//doi.org/10.57760/sciencedb.08547。 相似文献
18.
针对传统目标检测方法在水下识别任务中误检率较高的问题,基于一阶段全卷积检测器(FCOS)引入多尺度特征选择及中心边界特征选择,实现高精度水下目标检测。模型中的自适应加权融合特征金字塔通过设置可学习权重加权融合所有的特征层级,实现多尺度空间特征选择。此外,为了处理检测中分类和回归任务之间的特征耦合问题,并分离不同任务之间的共享特征,设计了基于空间特征解耦的检测头,实现了中心和边界区域的特征选择。实验中,针对水下数据集URPC2018和UWD2021进行性能测试,并与先进的目标检测方法进行对比。大量的实验结果表明,基于空间特征选择的FCOS模型在水下检测任务中展现出优异的性能,在URPC2018和UWD2021上的类平均精度(mean Average Precision,mAP)分别为82.7%和83.3%。 相似文献
19.
Layne C. Bradley 《Information Systems Management》2013,30(1):21-28
Abstract Planning and implementing a data communications network is a complex task involving organizational as well as technical issues. The network design process must be integrated with the organization's business goals and strategies. Because network planning, implementation, and maintenance require skills not usually found in a batch-oriented DP environment, training is critical. 相似文献
20.
Imran Ahmed Sadia Din Gwanggil Jeon Francesco Piccialli Giancarlo Fortino 《IEEE/CAA Journal of Automatica Sinica》2021,8(7):1253-1270
Collaborative Robotics is one of the high-interest research topics in the area of academia and industry. It has been progressively utilized in numerous applications, particularly in intelligent surveillance systems. It allows the deployment of smart cameras or optical sensors with computer vision techniques, which may serve in several object detection and tracking tasks. These tasks have been considered challenging and high-level perceptual problems, frequently dominated by relative information about the environment, where main concerns such as occlusion, illumination, background, object deformation, and object class variations are commonplace. In order to show the importance of top view surveillance, a collaborative robotics framework has been presented. It can assist in the detection and tracking of multiple objects in top view surveillance. The framework consists of a smart robotic camera embedded with the visual processing unit. The existing pre-trained deep learning models named SSD and YOLO has been adopted for object detection and localization. The detection models are further combined with different tracking algorithms, including GOTURN, MEDIANFLOW, TLD, KCF, MIL, and BOOSTING. These algorithms, along with detection models, help to track and predict the trajectories of detected objects. The pre-trained models are employed; therefore, the generalization performance is also investigated through testing the models on various sequences of top view data set. The detection models achieved maximum True Detection Rate 93% to 90% with a maximum 0.6% False Detection Rate. The tracking results of different algorithms are nearly identical, with tracking accuracy ranging from 90% to 94%. Furthermore, a discussion has been carried out on output results along with future guidelines. 相似文献