作者：
Bian, YuanLiu, MinWang, XuepingMa, YunfengWang, YaonanHunan University
National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University
Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China
Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider...
详细信息
As an crucial component of power line, the timely check for the state of insulator is necessary for the normal running of transmission lines. In view of debasement of insulator segmentation accuracy in current transmi...
详细信息
ISBN:
(纸本)9781665479691
As an crucial component of power line, the timely check for the state of insulator is necessary for the normal running of transmission lines. In view of debasement of insulator segmentation accuracy in current transmission line caused by complex background, low contrast, and the quality of images is not guaranteed, we improve U-Net by combining attention mechanism and residual connection. Residual connection is added to the encoder part to improve the extraction of low-level semantic information, and the attention mechanism is added to the decoder part for integrating high and low level features better and reduce the error between them. We confirm the effectiveness of the improved module through experiments, while the results showing that the improved U-Net model segmentation performance on insulator dataset is improved from 0.875 to 0.912. And our method also outperforms previous segmentation work on insulator dataset.
The working state of fasteners is closely related to the safe and stable operation of the power grid. However, the performance of the existing fastener defect detection models is not enough to meet the requirements, b...
详细信息
ISBN:
(纸本)9781665479691
The working state of fasteners is closely related to the safe and stable operation of the power grid. However, the performance of the existing fastener defect detection models is not enough to meet the requirements, because the size of object is small, the environment is complex, the sample size is unbalanced and so on. Therefore, we design a simple but effective feature fusion method, called Double Context Information Enhancement Module. The model can fully learn the features of fasteners by expanding the receptive field of the feature map during the construction of the feature pyramid, and the feature expression ability of fasteners can be enhanced by learning the features of adjacent layers after the construction of the feature pyramid. Through experiments, we proved that DCEM can improve about 8.8AP compared with the original model, and at the same time, the effectiveness and advancement of DCEM are proved by comparing with SOTA.
In this paper, we study the fault detection along with the estimation problem for an unstable wave equation based on an adaptive extended state observer (ESO) using only boundary measurements. A fault detection filter...
详细信息
Emerging universal Computational Aberration Correction (CAC) paradigms provide an inspiring solution to light-weight and high-quality imaging without repeated data preparation and model training to accommodate new len...
详细信息
Emerging universal Computational Aberration Correction (CAC) paradigms provide an inspiring solution to light-weight and high-quality imaging without repeated data preparation and model training to accommodate new lens designs. However, the training databases in these approaches, i.e., the lens libraries (LensLibs), suffer from their limited coverage of real-world aberration behaviors. Moreover, it is challenging to train a universal model for reliable results in a zero-shot manner, whose inflexible tuning pipeline is also confined to the lens-descriptions-known case. In this work, we set up an OmniLens framework for universal CAC, considering both the generalization ability and flexibility. OmniLens extends the idea of universal CAC to a broader concept, where a base model is trained as the pre-trained model for three cases, including zero-shot CAC with the pre-trained model, few-shot CAC with a little lens-specific data for fine-tuning, and domain adaptive CAC using domain adaptation for lens-descriptions-unknown lens. In terms of OmniLens’s data foundation, we first propose an Evolution-based Automatic Optical Design (EAOD) pipeline to construct the LensLib automatically, coined AODLib, whose diversity is enriched by an evolution framework, with comprehensive constraints and a hybrid optimization strategy for achieving realistic aberration behaviors. For network design, we introduce the guidance of high-quality codebook priors to facilitate both zero-shot CAC and few-shot CAC, which enhances the model’s generalization ability, while also boosting its convergence in a few-shot case. Furthermore, based on the statistical observation of dark channel priors in optical degradation, we design an unsupervised regularization term to adapt the base model to the target descriptions-unknown lens using its aberration images without ground truth. We validate the proposed OmniLens framework on 4 manually designed low-end lenses with various structures and aberration behaviors.
Affordance refers to the functional properties that an agent perceives and utilizes from its environment, and is key perceptual information required for robots to perform actions. This information is rich and multimod...
详细信息
Dynamic jumping on high platforms and over gaps differentiates legged robots from wheeled counterparts. Compared to walking on rough terrains, dynamic locomotion on abrupt surfaces requires fusing proprioceptive and e...
详细信息
In server board assembly tasks, the effect of vision-based robot assembly schemes is not ideal due to the small installation gap and the blocking of vision. Adding force sensors and force controllers can be a good sol...
详细信息
ISBN:
(数字)9798350340266
ISBN:
(纸本)9798350340273
In server board assembly tasks, the effect of vision-based robot assembly schemes is not ideal due to the small installation gap and the blocking of vision. Adding force sensors and force controllers can be a good solution to the above problems and increase the flexibility in the assembly process. In this paper, we propose a force control strategy applied to a server board assembly task. The method is divided into two main parts. In the first part, the zero offset of the force sensor and the load gravity are calibrated and compensated, so that the external force on the load is accurately obtained. In the second part, the admittance controller is designed to achieve compliant behavior between the robot and the environment. Finally, the experimental verification of the board insertion is carried out on the experimental platform. Experimental results verify the effectiveness and practicability of the proposed method.
Detecting moving objects in the stationary background is an important problem in visual surveillance ***,the traditional background subtraction method fails when the background is not completely stationary and involve...
详细信息
Detecting moving objects in the stationary background is an important problem in visual surveillance ***,the traditional background subtraction method fails when the background is not completely stationary and involves certain dynamic *** this paper,according to the basic steps of the background subtraction method,a novel non-parametric moving object detection method is proposed based on an improved ant colony algorithm by using the Markov random ***,the contributions are as follows:1)A new nonparametric strategy is utilized to model the background,based on an improved kernel density estimation;this approach uses an adaptive bandwidth,and the fused features combine the colours,gradients and positions.2)A Markov random field method based on this adaptive background model via the constraint of the spatial context is proposed to extract objects.3)The posterior function is maximized efficiently by using an improved ant colony system *** experiments show that the proposed method demonstrates a better performance than many existing state-of-the-art methods.
In this paper we propose a novel sparse optical flow (SOF)-based line feature tracking method for the camera pose estimation problem. This method is inspired by the point-based SOF algorithm and developed based on an ...
详细信息
暂无评论