Non-maximum Suppression for Object Detection by Passing Messages Between Windows
نویسندگان
چکیده
Non-maximum suppression (NMS) is a key post-processing step in many computer vision applications. In the context of object detection, it is used to transform a smooth response map that triggers many imprecise object window hypotheses in, ideally, a single bounding-box for each detected object. The most common approach for NMS for object detection is a greedy, locally optimal strategy with several hand-designed components (e.g., thresholds). Such a strategy inherently suffers from several shortcomings, such as the inability to detect nearby objects. In this paper, we try to alleviate these problems and explore a novel formulation of NMS as a well-defined clustering problem. Our method builds on the recent Affinity Propagation Clustering algorithm, which passes messages between data points to identify cluster exemplars. Contrary to the greedy approach, our method is solved globally and its parameters can be automatically learned from training data. In experiments, we show in two contexts – object class and generic object detection – that it provides a promising solution to the shortcomings of the greedy NMS.
منابع مشابه
Max-Margin Object Detection
Most object detection methods operate by applying a binary classifier to sub-windows of an image, followed by a non-maximum suppression step where detections on overlapping sub-windows are removed. Since the number of possible sub-windows in even moderately sized image datasets is extremely large, the classifier is typically learned from only a subset of the windows. This avoids the computation...
متن کاملIndividualness and Determinantal Point Processes for Pedestrian Detection
In this paper, we introduce individualness of detection candidates as a complement to objectness for pedestrian detection. The individualness assigns a single detection for each object out of raw detection candidates given by either object proposals or sliding windows. We show that conventional approaches, such as non-maximum suppression, are sub-optimal since they suppress nearby detections us...
متن کاملNon Maximal Suppression in Cascaded Ranking Models
Ranking models have recently been proposed for cascaded object detection, and have been shown to improve over regression or binary classification in this setting [1, 2]. Rather than train a classifier in a binary setting and interpret the function post hoc as a ranking objective, these approaches directly optimize regularized risk objectives that seek to score highest the windows that most clos...
متن کاملبهبود کارایی پروتکلSIP در شرایط اضافه بار با استفاده از قابلیت مبتنی بر پنجره
The extent and diversity of systems provided by IP networks have made various technologies to approach integrating various types of access networks and converting to next generation network. The Session Initiation Protocol (SIP) with respect to facilities such as being in text form, end-to-end connection, independence from the type of transmitted data, and supporting various forms of transmissi...
متن کاملAutomatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report
In this report, we present a system that can automatically detect and 3D reconstruct the target objects. After the reconstruction, users can edit the image by scaling, translating, rotating and deleting the target objects. The system consists of three parts. The first part is the detection part. We use HOG (Histogram of Gradient) template matching for detection and adopt sliding window strategy...
متن کامل