Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366375071> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4366375071 abstract "The present work aims to design and implement Digital Image Processing, which is a Numpy and LSTM- based detection kit. The combination has plenty of applications such as hand gesture recognition, sign language translators, home security systems, traffic control technologies, intruder recognition systems, etc. The current investigation utilizes the application for threat detection and rescue system. We have implemented a detection kit for hand gesture tracking and identification of the hand sign which signifies ‘threat’ that consists of two major units namely hardware and software. The hardware part comprises a camera that captures frames in the desired detection range. The detection and identification of the threat is recognized using the following software units such as Anaconda Navigator, Jupyter Notebook, NumPy library, TensorFlow, OpenCV, and MediaPipe. At first, the inputdata is trained for the key-points identification and then the camera captures the frame and compares it with the trained data set. When the captured key point which is hand-signed by the victim is similar to the key points of the trained data set, the threat is detected. The frames are re-evaluated thrice for an accurate result. This is then notified to the officials for rescue. The major advantage of this novel work is the less re-evaluation time and efficient frame process in a very short duration of time. It is also a low-cost system that produces a highly reliable result. This detection will certainly help to save a life and assure a protected life for people in society." @default.
- W4366375071 created "2023-04-21" @default.
- W4366375071 creator A5000480548 @default.
- W4366375071 creator A5001585301 @default.
- W4366375071 creator A5066544373 @default.
- W4366375071 date "2023-03-01" @default.
- W4366375071 modified "2023-09-27" @default.
- W4366375071 title "Threat Detection and Rescue using Machine Learning" @default.
- W4366375071 cites W2146292423 @default.
- W4366375071 cites W2767072113 @default.
- W4366375071 cites W2783764669 @default.
- W4366375071 cites W2912776959 @default.
- W4366375071 cites W2971145620 @default.
- W4366375071 cites W4210550054 @default.
- W4366375071 cites W4285503423 @default.
- W4366375071 cites W4285815800 @default.
- W4366375071 cites W4306964668 @default.
- W4366375071 cites W4308654528 @default.
- W4366375071 doi "https://doi.org/10.1109/esci56872.2023.10100234" @default.
- W4366375071 hasPublicationYear "2023" @default.
- W4366375071 type Work @default.
- W4366375071 citedByCount "0" @default.
- W4366375071 crossrefType "proceedings-article" @default.
- W4366375071 hasAuthorship W4366375071A5000480548 @default.
- W4366375071 hasAuthorship W4366375071A5001585301 @default.
- W4366375071 hasAuthorship W4366375071A5066544373 @default.
- W4366375071 hasConcept C111919701 @default.
- W4366375071 hasConcept C116834253 @default.
- W4366375071 hasConcept C126042441 @default.
- W4366375071 hasConcept C153180895 @default.
- W4366375071 hasConcept C154945302 @default.
- W4366375071 hasConcept C177264268 @default.
- W4366375071 hasConcept C199360897 @default.
- W4366375071 hasConcept C207347870 @default.
- W4366375071 hasConcept C26517878 @default.
- W4366375071 hasConcept C2776151529 @default.
- W4366375071 hasConcept C2777904410 @default.
- W4366375071 hasConcept C31972630 @default.
- W4366375071 hasConcept C3261483 @default.
- W4366375071 hasConcept C38652104 @default.
- W4366375071 hasConcept C41008148 @default.
- W4366375071 hasConcept C59822182 @default.
- W4366375071 hasConcept C76155785 @default.
- W4366375071 hasConcept C79403827 @default.
- W4366375071 hasConcept C86803240 @default.
- W4366375071 hasConcept C98045186 @default.
- W4366375071 hasConceptScore W4366375071C111919701 @default.
- W4366375071 hasConceptScore W4366375071C116834253 @default.
- W4366375071 hasConceptScore W4366375071C126042441 @default.
- W4366375071 hasConceptScore W4366375071C153180895 @default.
- W4366375071 hasConceptScore W4366375071C154945302 @default.
- W4366375071 hasConceptScore W4366375071C177264268 @default.
- W4366375071 hasConceptScore W4366375071C199360897 @default.
- W4366375071 hasConceptScore W4366375071C207347870 @default.
- W4366375071 hasConceptScore W4366375071C26517878 @default.
- W4366375071 hasConceptScore W4366375071C2776151529 @default.
- W4366375071 hasConceptScore W4366375071C2777904410 @default.
- W4366375071 hasConceptScore W4366375071C31972630 @default.
- W4366375071 hasConceptScore W4366375071C3261483 @default.
- W4366375071 hasConceptScore W4366375071C38652104 @default.
- W4366375071 hasConceptScore W4366375071C41008148 @default.
- W4366375071 hasConceptScore W4366375071C59822182 @default.
- W4366375071 hasConceptScore W4366375071C76155785 @default.
- W4366375071 hasConceptScore W4366375071C79403827 @default.
- W4366375071 hasConceptScore W4366375071C86803240 @default.
- W4366375071 hasConceptScore W4366375071C98045186 @default.
- W4366375071 hasLocation W43663750711 @default.
- W4366375071 hasOpenAccess W4366375071 @default.
- W4366375071 hasPrimaryLocation W43663750711 @default.
- W4366375071 hasRelatedWork W1583524169 @default.
- W4366375071 hasRelatedWork W1967456564 @default.
- W4366375071 hasRelatedWork W2065946851 @default.
- W4366375071 hasRelatedWork W2396501236 @default.
- W4366375071 hasRelatedWork W2567005852 @default.
- W4366375071 hasRelatedWork W2783980107 @default.
- W4366375071 hasRelatedWork W2904509960 @default.
- W4366375071 hasRelatedWork W2990559186 @default.
- W4366375071 hasRelatedWork W3120243212 @default.
- W4366375071 hasRelatedWork W3157384330 @default.
- W4366375071 isParatext "false" @default.
- W4366375071 isRetracted "false" @default.
- W4366375071 workType "article" @default.