Single Shot MultiBox Detector is a single shot detector (uses a single shot) for multiple categories, which is faster than the latest generation such as YOLO (You only look once) and significantly more accurate, in fact just as accurate. As well as the slower techniques, which make explicit region proposals and collection (including faster R-CNN). SSD predicts category scores and box offsets for a fixed set of default bounding boxes, using small convolutional filters applied on feature maps. Recent researches in object detection are driven by the success of convolutional neural networks (CNN). They are able to learn rich features outperforming hand-crafted features. To obtain high detection accuracy, we produce predictions of different scales from feature maps of different scales, and explicit predictions based on the aspect ratio. These design features lead to simple end-to-end training and high accuracy, even on low resolution input images, further improving speed and accuracy with precision [2]. The SSD only needs an input image and truth boxes for each object during training. Convolutely, we evaluate a small set of boxes implicit by different aspect ratios at each location, in several feature maps with different [3]. For each implicit box, we preach both shape offsets and confidences for all object categories. During training, for the first time these default boxes match the truth boxes. The SSD approach is based on a convolutional feed-forward network that produces a fixed size collection of bounding boxes and scores for the presence of object class instances in those boxes, followed by a non-maximal suppression step to produce the final detections.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.