About this document
CNN-LSTM for Shadow Detection in Videos by reetashukla992 is a document available to read on EtoBox.
This dissertation presents a hybrid CNN-LSTM model for classifying video frames into clean, artifact, and shadow categories to improve motion detection in surveillance systems. Utilizing the LaSIESTA dataset and Niblack thresholding for preprocessing, the model effectively captures spatial and temporal features, demonstrating robust performance in distinguishing shadows from actual motion. The research highlights the significance of spatiotemporal modeling in enhancing video analysis tasks and addresses cha
- Author
- reetashukla992
- Language
- EN