Lamp control system with function of dynamic gesture recognition
A dynamic gesture and control system technology, applied in energy-saving control technology, character and pattern recognition, light circuit layout, etc., can solve the problem of short control distance of light switch control equipment, and achieve easy construction and maintenance, long control distance, excellent The effect of scalability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0021] Specific implementation mode one: see figure 1 Describe this embodiment, a lamp control system for recognizing dynamic gestures described in this embodiment, which includes a main controller 1, a dynamic gesture acquisition device 2 and a dynamic gesture processing module 3;
[0022] The dynamic gesture acquisition device 2 is used to capture the video data of the dynamic gesture of the operator, and send the collected video data to the dynamic gesture processing module 3;
[0023] A preset gesture track template is stored in the database of the dynamic gesture processing module 3;
[0024] The dynamic gesture processing module 3 recognizes the hand image information in the received video data, and after detecting the hand image information, tracks the movement trajectory of the hand, and records the movement trajectory of the hand, and records the hand movement trajectory The motion trajectory of the dynamic gesture input trajectory is matched with the preset gesture ...
specific Embodiment approach 2
[0031] Specific implementation mode two: see figure 1 Describe this embodiment. The difference between this embodiment and the lamp control system for recognizing dynamic gestures described in Embodiment 1 is that the dynamic gesture processing module 3 uses a correlation filter tracking algorithm to track the movement trajectory of the hand. accomplish.
[0032] In this embodiment, when a human hand is detected, it is necessary to record the hand trajectory in order to obtain dynamic gestures. The present invention is based on real-time and accuracy requirements, and at the same time, considering that the hand scale changes in the application scene are small, the present invention adopts a tracking algorithm based on correlation filtering to track the hand trajectory, and the tracking algorithm of the correlation filtering can use hand The gray value trains the feature model in real time to track the hand. Since the gray value is directly used as the feature in this process...
specific Embodiment approach 3
[0033] Specific implementation mode three: see figure 1 Describe this embodiment. The difference between this embodiment and the lamp control system for recognizing dynamic gestures described in Embodiment 1 is that, when the hand image information is detected, the movement trajectory of the hand is tracked and the hand is recorded. The motion trajectory of the recorded hand is used as the dynamic gesture input trajectory to match the preset gesture trajectory template, and the specific process of sending the matching result to the main controller 1 is as follows:
[0034] Step 1: Determine the initial target frame according to the initial position of the hand;
[0035] Step 2: Extract the hand grayscale feature in the initial target frame, and the hand grayscale feature is used as the initial feature template;
[0036] Step 3: Read the next frame of video image, make the initial feature template traverse the whole image of the frame, and match it with the hand grayscale feat...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More