Because the sowing performance of precision rice seeders is influenced not only by the operational parameters but also by the physical properties of seeds, during the rice seedling nursery process, sowing quantity in plug tray varies from time to time. Therefore, monitoring of sowing quantity by workers is needed. In order to solve the problem that human labor spends much time on working in outdoor environment and its low efficiency, a rice nursery tray images wireless transmission system based on embedded machine vision was designed. The embedded machine vision system was composed of embedded development platform Tiny4412, WiFi gateway, network camera, infrared sensor module and remote computer. The embedded Linux operating system, camera driver, GPIO port driver and network file system configuration were installed in embedded development platform. Applications for the device were programmed with Qt development tool. The applications included image acquisition, real-time images displaying on screen and friendly interactive interface. Jpeglib static library was used to compress the images. Through the WiFi network, embedded system and remote server achieved socket communication in accordance with the provision of protocol data transmission. The remote server achieved collecting, validating, displaying and saving the images based on the Netty framework. The test results showed that the transmission of BMP and the compressed JPEG images could meet the operational requirements of automated rice sowing test line. The transmission rate of JPEG images was greatly improved. The embedded data acquisition terminal could collect stable seeding tray images, and successfully upload to the server. The network average packet loss rate was 0.23% and the error rate was 0.23%. The design of the system laid the experimental platform for the achievement of remote control to the rice sowing quantity of rice sowing test line and the development of embedded-machine-vision-based system for rice nursery trays sowing quantity detection.