The invention discloses an underwater fry, young shrimp and young crab quantity estimating and behavior monitoring device and method based on computer vision. The device is characterized in that the device comprises a two-way winch, a motor, a floater and a video collecting device, wherein the two-way winch and the motor are used for driving the video collecting device to carry out all-dimensional and different-water-level sampling in a nursery pond, the floater is used for bearing the motor, and the video collecting device is used for collecting young videos of fry, young shrimps and young crabs. The method comprises the following steps that the video collecting device is arranged in water and is respectively driven by the two-way winch and the motor to collect the videos of the fry, the young shrimps and the young crabs in the nursery pond, and the quantity and the density of the fry, the young shrimps and the young crabs in the whole nursery pond are estimated by using an image processing technology according to collected fry, young shrimp and young crab images of different water levels and different dimensions; a light inducing light source is turned on, and the shot videos are used in the image processing technology to calculate the swimming speed of targets and a cluster center coordinate to reflect the moving capability and light inducing capability of the fry, the young shrimps and the young crabs. The underwater fry, young shrimp and young crab quantity estimating and behavior monitoring device has the advantages of being simple in structure, wide in monitoring range, convenient to use and high in accuracy, and is suitable for biological quantity estimation and behavior monitoring on the nursing state of automated aquaculture.