街景变化检测对于自然灾害破坏和城市发展变化的研究起着重要作用.其主要目标是将成对的输入图片中变化的区域标注出来,其实质是二分类的语义分割问题.不同时间拍摄的街景图片可能受到如光线、天气、背景噪声、视角误差等诸多干扰因素的影响,这给传统的变化检测方法带来挑战.针对该问题,提出了一种新的神经网络模型(Multiple Difference Features Network,MDFNet).该模型首先使用孪生网络提取成对输入图片的不同深度特征,并使用差异模块对相同深度特征计算差异,以此有效获得不同尺度的变化信息;然后通过JPU模块融合多重差异特征,在不损失细节信息的情况下提取其深层语义信息;最后使用金字塔池化模块结合全局和局部信息生成二分类的变化检测图像.在PCD数据集上的GSV和TSUNAMI部分分别采用5折交叉验证法对模型进行实验,实验结果表明,MDFNet获得了0.787和0.862的F-score,相比排名第二的DOF-CDNet方法,其值提高了约11.9%和2.9%,同时其能够更精准地分割变化细节.因此,所提模型可以有效应对干扰,对于复杂场景也具备优秀的检测能力. 相似文献
In this paper, a fault estimator with linear fractional transformation (LFT) parameter dependency is designed for the linear parameter‐varying (LPV) system of the aero‐engine with both sensor and actuator faults under disturbances. After an aero‐engine affine parameter‐dependent LPV model is derived by the linear fitting method and matrix pseudo‐inverse method, the LPV model with disturbances and fault signals is transformed into a LFT structure. Based on the full block S‐procedure, the sufficient condition for the existence of the fault estimator is proposed, which can lead to less conservative results. Then the fault estimator design algorithm which can adjust to the current system dynamic adaptively is presented. Finally, a fault estimator is designed for a turbofan aero‐engine under multiple types of faults and disturbances to demonstrate the effectiveness of the proposed method. 相似文献
Recent advances in deep learning have enabled robots to grasp objects even in complex environments. However, a large amount of data is required to train the deep-learning network, which leads to a high cost in acquiring the learning data owing to the use of an actual robot or simulator. This paper presents a new form of grasp data that can be generated automatically to minimize the data-collection cost. The depth image is converted into simplified grasp data called an irregular depth tile that can be used to estimate the optimal grasp pose. Additionally, we propose a new grasping algorithm that employs different methods according to the amount of free space in the bounding box of the target object. This algorithm exhibited a significantly higher success rate than the existing grasping methods in grasping experiments in complex environments.