| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| searchwing-bilderkennung [2019/05/30 23:47] – wf68spef | searchwing-bilderkennung [2021/05/31 22:03] (current) – added SE2 Projektarbeit Kamera beckmanf |
|---|
| |
| By analysing the image with we receive from the camera, we can detect boats on the sea. To achieve this, different algorithms and approaches from the image processing and deep learning domain can be used. | By analysing the image with we receive from the camera, we can detect boats on the sea. To achieve this, different algorithms and approaches from the image processing and deep learning domain can be used. |
| | |
| | ===== Camera ===== |
| | |
| | {{ ::g2-picam.pdf | S. Keller, K. Dierig, L. Range, "SearchWing - Messung des Energieverbrauchs eines Raspberry Pi und Charakterisierung des Kamersystems", Projektarbeit, WS 2020/21}} |
| | |
| | ===== Compression effects on detection ===== |
| | |
| | Does JPEG image compression affect detection? See |
| | |
| | [[https://doi.org/10.1117/1.JMI.6.2.027501|Farhad Ghazvinian Zanjani, Svitlana Zinger, Bastian Piepers, Saeed Mahmoudpour, Peter Schelkens, and Peter H. N. de With "Impact of JPEG 2000 compression on deep convolutional neural networks for metastatic cancer detection in histopathological images," Journal of Medical Imaging 6(2), 027501 (24 April 2019). https://doi.org/10.1117/1.JMI.6.2.027501]] |
| |
| ===== Detection by using edgedetector and a 2d tracker in world coordinates ===== | ===== Detection by using edgedetector and a 2d tracker in world coordinates ===== |
| | |
| | {{:ros.jpg?nolink&1311x744|ros.jpg}} |
| |
| ==== Code ==== | ==== Code ==== |
| * Visualization of the detection in digikam | * Visualization of the detection in digikam |
| |
| {{data:image/png;base64,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 |