Low latency video transmission is gaining importance in time-critical applications using real-time cloud-based systems. Cloud-based Virtual Reality (VR), remote control, and AI response systems are emerging use cases that demand low latency and good reliability. Although there are many video transmission schemes that claim low latency, they vary over different network conditions. Therefore, it is necessary to develop methods that can accurately measure end-to-end latency online, continuously, without any content modification. This research brings these applications one step closer to addressing these next generation use cases. This paper analyzes the cause of end-to-end latency within a video transmission system, and then proposes three methods to measure the latency: timecode, remote online, and lossless remote video online. The corresponding equipment was designed and implemented. The actual measurement of the three methods using related equipment proved that our proposed method can accurately and effectively measure the end-to-end latency of the video transmission system.

Separating printed or handwritten characters from a noisy background is valuable for many applications including test paper autoscoring. The complex structure of Chinese characters makes it difficult to obtain the goal because of easy loss of fine details and overall structure in reconstructed characters. This paper proposes a method for separating Chinese characters based on generative adversarial network (GAN). We used ESRGAN as the basic network structure and applied dilated convolution and a novel loss function that improve the quality of reconstructed characters. Four popular Chinese fonts (Hei, Song, Kai, and Imitation Song) on real data collection were tested, and the proposed design was compared with other semantic segmentation approaches. The experimental results showed that the proposed method effectively separates Chinese characters from noisy background. In particular, our methods achieve better results in terms of Intersection over Union (IoU) and optical character recognition (OCR) accuracy.

No abstract

No abstract

No abstract