Intelligent lamp post distress system and method
A technology of smart lights and light poles, applied in transmission systems, closed-circuit television systems, televisions, etc., can solve problems such as inability to effectively call for help, and achieve the effect of improving rescue efficiency and facilitating expansion.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] At this stage, street lamps basically only have lighting functions, while smart light poles have many functional modules, generally equipped with large screens, smart lights, etc. Computing capabilities to recognize gestures and voices, as well as remind passers-by to pay attention and deter criminals. And the smart light poles can communicate directly or indirectly through the control center as a transfer station, which also enables any light pole in the light pole cluster to coordinate with other light poles to process the call for help or broadcast the call for help after it sends out a call for help. Request signals became possible.
[0041] This embodiment is a smart light pole call for help system, such as figure 1 As shown, the system includes the following modules:
[0042] Bullet cameras, that is, routinely used monitors placed on light poles, also have the function of capturing pedestrian gestures in the distance.
[0043] Smart lights can automatically adj...
Embodiment 2
[0051] This embodiment is a flow chart of a method for using the smart light pole system to issue a call for help by recognizing gestures. Such as figure 2 As shown, the method includes the following steps;
[0052]Adjust the gun camera and the low-position wide-angle camera to normal operation; send the pictures collected by the two cameras to the cloud server in real time according to a certain interval and frequency, and then perform image processing such as noise reduction on the received pictures in the cloud, and then send them to the cloud server. into the SSD model to segment gestures. In the next step, the segmented gestures are fed into the CNN model for classification. After classification, the probability that the gesture belongs to various other gestures is obtained, and the gesture type corresponding to the maximum probability in the detection result is regarded as the category of the gesture, and then it is judged whether the recognized gesture is a specified...
Embodiment 3
[0058] This embodiment is a flow chart of a method for using the smart light pole system to issue a call for help by recognizing voice, as shown in image 3 As shown, the method includes the following steps;
[0059] Turn on the microphone to collect external voice information, the voice information does not support MP3 format, here choose wav format. Then the wav format is preprocessed and feature extraction is performed as a matrix vector. Then combine the acoustic model and the voice model to decode the voice and turn it into a text sequence. It is considered that the text sequence obtained at this time is the recognized text, and then compare the text with the preset text to determine whether it is a distress text. If it is not the specified text, continue to recognize the next paragraph of text; if it is the specified distress voice, then immediately send a distress request signal to the control center, and gradually develop the control right of this smart light pole to ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


