Video monitoring method and video monitoring device

A video monitoring device, comprising:

• a video data acquiring module for acquiring video data in an acquisition scene;
• an amount determining module for inputting at least one frame in the video data into a first neural network that is trained in advance, so as to determine object amount information of each pixel dot in the at least one frame;
• and
• a density determining module for executing at least one of the following operations by using a second neural network that is trained in advance:
• performing a smoothing operation based on the object amount information in the at least one frame so as to rectify the object amount information;
• determining object density information of each pixel dot in the at least one frame based on scene information of the acquisition scene for the video data and the object amount information in the at least one frame;
• and
• predicting object density information of each pixel dot in a to-be-predicted frame next to the at least one frame based on the scene information of the acquisition scene for the video data, the object amount information in the at least one frame, and association information between the at least one frame and the to-be-predicted frame.

A video monitoring device, comprising:

• a processor;
• a memory;
• and
• computer program instructions stored in the memory and configured to execute the following steps when being run by the processor:
• obtaining video data acquired by a video data acquiring module;
• inputting at least one frame in the video data into a first neural network that is trained in advance, so as to determine object amount information of each pixel dot in the at least one frame;
• and
• executing at least one of the following operations by using a second neural network that is trained in advance:
• performing a smoothing operation based on the object amount information in the at least one frame so as to rectify the object amount information;
• determining object density information of each pixel dot in the at least one frame based on scene information of the acquisition scene for the video data and the object amount information in the at least one frame;
• predicting object density information of each pixel dot in a to-be-predicted frame next to the at least one frame based on the scene information of the acquisition scene for the video data, the object amount information in the at least one frame, and association information between the at least one frame and the to-be-predicted frame.