Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

3results about How to "Prevent misidentification" patented technology

Touch display devices and sensing methods with active pens

ActiveCN115877968Bprevent misidentificationInput/output processes for data processingActive penTouch Senses
This invention proposes a touch display device for use with an active pen. During touch sensing, the touch position is detected. During active pen sensing, an uplink signal is transmitted and a downlink signal is detected. When a downlink signal is detected, it is determined whether the distance between the active pen position and the touch position is less than or equal to a first preset distance; if so, the device does not enter active pen mode.
Owner:HIMAX TECH LTD

Multi-source remote sensing image enhancement method and device, equipment and storage medium

ActiveCN121961898AAvoid Generalization Insufficiencyprevent misidentificationImage enhancementImage analysisHigh spatial resolutionImage resolution
The invention discloses a multi-source remote sensing image enhancement method, device and equipment and a storage medium, and the method comprises the steps: collecting a multi-source remote sensing image, carrying out the preprocessing of the multi-source remote sensing image, and constructing an initial image sample library; performing distortion elimination processing on the first-resolution image in the initial image sample library, and performing correction processing on the second-resolution image to obtain a paired image sample library; constructing a deep learning resolution enhancement network combining a stacked architecture and an attention mechanism; a progressive training strategy is adopted, and the target image sample library is utilized to train the deep learning resolution enhancement network; and inputting a to-be-enhanced remote sensing image into the well-trained deep learning resolution enhancement network to generate an enhanced multi-source remote sensing image. According to the method, through sample library construction, distortion elimination, network design and a training strategy, the generated image gives consideration to high spatial resolution and high temporal resolution at the same time, and the generalization ability and the enhancement effect of the model are enhanced.
Owner:长江水利委员会网络与信息中心