Not maximum suppression on detection windows

Question

In the literature on detecting objects, the classifier and the sliding window approach are usually used to detect the presence of objects in the image, this method returns a set of detection windows, and detection overlaps are resolved using not the maximum suppression.

Can someone explain the algorithm for doing not the maximum suppression in these detection windows.

thanks

Answer 1

Quote from http://www.di.ens.fr/willow/events/cvml2012/materials/practical-detection/

Classifying window-style scan patterns usually results in multiple responses around the target. The standard practice for dealing with this is to remove any detector responses in the vicinity of the detection with a locally maximum confidence level (non-maximum vibration suppression or NMS). NMS is usually applied to all image detections with confidence above a certain threshold. Try NMS face detection for different thresholds and in different images:

Also here http://www.ens-lyon.fr/LIP/Arenaire/ERVision/detection_exercise_solution.m you can find the matlab program that does everything - detection and NMS in the detection windows

Code that does not suppress maximally in detection windows,

%%%%%%%%%%%%%%% ************************************************************** %%%%%%%%%%%%%%% ************************************************************** %%%%%%%%%%%%%%% * * %%%%%%%%%%%%%%% * EXERCISE 3: * %%%%%%%%%%%%%%% * * %%%%%%%%%%%%%%% * Non-maxima suppression of multiple responses * %%%%%%%%%%%%%%% * * %%%%%%%%%%%%%%% ************************************************************** %%%%%%%%%%%%%%% ************************************************************** %%%%%%%%%%%%%%% %%%%%%%%%%%%%%% Scanning-window style classification of image patches typically %%%%%%%%%%%%%%% results in many multiple responses around the target object. %%%%%%%%%%%%%%% A standard practice to deal with this is to remove any detector %%%%%%%%%%%%%%% responses in the neighborhood of detections with locally maximal %%%%%%%%%%%%%%% confidence scores (non-maxima suppression or NMS). NMS is %%%%%%%%%%%%%%% usually applied to all detections in the image with confidence %%%%%%%%%%%%%%% above certain threshold. %%%%%%%%%%%%%%% %%%%%%%%%%%%%%% TODO: %%%%%%%%%%%%%%% 3.1 Try out different threshold values to pre-selected windows %%%%%%%%%%%%%%% passed to the NMS stage, see parameter 'confthresh' below. %%%%%%%%%%%%%%% 3.2 Try out different threshold values for NMS detections, %%%%%%%%%%%%%%% see parameter 'confthreshnms' %%%%%%%%%%%%%%% 3.3 Try detection and with different thresholds for different %%%%%%%%%%%%%%% included images: 'img1.jpg', 'img2.jpg', 'img3.jpg', 'img4.jpg' %%%%%%%%%%%%%%% confthresh=0; indsel=find(conf>confthresh); [nmsbbox,nmsconf]=prunebboxes(bbox(indsel,:),conf(indsel),0.2); %%%%%%%%%%%%%%% display detections above threshold after non-max suppression %%%%%%%%%%%%%%% confthreshnms=1; clf, showimage(img) indsel=find(nmsconf>confthreshnms); showbbox(nmsbbox(indsel,:),[1 1 0],regexp(num2str(nmsconf(indsel)'),'\d+\.\d+','match')); title(sprintf('%d NMS detections above threshold %1.3f',size(nmsbbox,1),confthreshnms),'FontSize',14) fprintf('press a key...'), pause, fprintf('\n') 

You can find all related functions in the first link.