Attention! This forum will be made read-only by Dec-20. Please migrate to https://forum.opencv.org. Most of existing active users should've received invitation by e-mail.

# Revision history [back]

### Coordinates in contour not Accurate/smooth

I'm working on a people counter system and i'm getting the coordinate of each blob detected through the following code: if area>100: contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE) try: hierarchy = hierarchy[0] except: hierarchy = [] for contour, hier in zip(contours, hierarchy): (x,y,w,h) = cv2.boundingRect(contour) if w>40 and h>40:

    if x>400 and x<450:
if (abs(prev_x-x))>30:
cv2.circle(frame,(int(x),int(y)),10,(0,255,0),-1)
cv2.rectangle(frame, (x,y),(x+10,y+10), (255, 0, 0), 0)
j=j+1
prev_x=x


Now the coordinates from the rectangle i'm getting isn't smooth. Moreover the centre of circle i'm getting is'nt stable. Can anyone please suggest a better solution at getting the coordinates of each blob/contour smmothly which is not prone to noise and is stable? If there's a different algorithm available then please do suggest. Thanks.

### Coordinates in contour not Accurate/smooth

I'm working on a people counter system and i'm getting the coordinate of each blob detected through the following code: if area>100: code:

contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
try: hierarchy = hierarchy[0]
except: hierarchy = []
for contour, hier in zip(contours, hierarchy):
(x,y,w,h) = cv2.boundingRect(contour)
center = (int(x),int(y))
cv2.circle(frame,center,1,(0,255,0),-1)
if x>400 and x<450:
if (abs(prev_x-x))>30:
cv2.circle(frame,(int(x),int(y)),10,(0,255,0),-1)
cv2.rectangle(frame, (x,y),(x+10,y+10), (255, 0, 0), 0)
(abs(prev_x-x))>25:
cv2.circle(frame,center,1,(0,255,0),-1)
j=j+1
prev_x=x
Now the coordinates from the rectangle i'm getting isn't smooth. Moreover the centre of circle i'm getting is'nt stable. Can anyone please suggest a better solution at getting the coordinates of each blob/contour smmothly which is not prone to noise and is stable?
If there's a different algorithm available then please do suggest.
Thanks.  


 3 No.3 Revision updated 2016-04-20 16:39:04 -0500 Coordinates in contour not Accurate/smooth I'm working on a people counter system and i'm getting the coordinate of each blob detected through the following code: contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE) try: hierarchy = hierarchy[0] except: hierarchy = [] for contour, hier in zip(contours, hierarchy): (x,y),radius = cv2.minEnclosingCircle(contour) center = (int(x),int(y)) radius = int(radius) if radius>3: cv2.circle(frame,center,1,(0,255,0),-1) if x>400 and x<450: if (abs(prev_x-x))>25: cv2.circle(frame,center,1,(0,255,0),-1) j=j+1 prev_x=x Now the coordinates from the rectangle i'm getting isn't smooth. Moreover the centre of circle i'm getting is'nt stable. Can anyone please suggest a better solution at getting the coordinates of each blob/contour smmothly which is not prone to noise and is stable? stable? Mine is moving too waywardly and the moving of centres arent linear. If there's a different algorithm available then please do suggest. Thanks. 


 Copyright OpenCV foundation, 2012-2018. Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license. about | faq | help | privacy policy | terms of service Powered by Askbot version 0.10.2 Please note: OpenCV answers requires javascript to work properly, please enable javascript in your browser, here is how //IE fix to hide the red margin var noscript = document.getElementsByTagName('noscript')[0]; noscript.style.padding = '0px'; noscript.style.backgroundColor = 'transparent'; askbot['urls']['mark_read_message'] = '/s/messages/markread/'; askbot['urls']['get_tags_by_wildcard'] = '/s/get-tags-by-wildcard/'; askbot['urls']['get_tag_list'] = '/s/get-tag-list/'; askbot['urls']['follow_user'] = '/followit/follow/user/{{userId}}/'; askbot['urls']['unfollow_user'] = '/followit/unfollow/user/{{userId}}/'; askbot['urls']['user_signin'] = '/account/signin/'; askbot['urls']['getEditor'] = '/s/get-editor/'; askbot['urls']['apiGetQuestions'] = '/s/api/get_questions/'; askbot['urls']['ask'] = '/questions/ask/'; askbot['urls']['questions'] = '/questions/'; askbot['settings']['groupsEnabled'] = false; askbot['settings']['static_url'] = '/m/'; askbot['settings']['minSearchWordLength'] = 4; askbot['settings']['mathjaxEnabled'] = false; askbot['settings']['sharingSuffixText'] = ''; askbot['settings']['errorPlacement'] = 'after-label'; askbot['data']['maxCommentLength'] = 800; askbot['settings']['editorType'] = 'markdown'; askbot['settings']['commentsEditorType'] = 'rich\u002Dtext'; askbot['messages']['askYourQuestion'] = 'Ask Your Question'; askbot['messages']['questionSingular'] = 'question'; askbot['messages']['answerSingular'] = 'answer'; askbot['messages']['acceptOwnAnswer'] = 'accept or unaccept your own answer'; askbot['messages']['followQuestions'] = 'follow questions'; askbot['settings']['allowedUploadFileTypes'] = [ "jpg", "jpeg", "gif", "bmp", "png", "tiff" ]; askbot['data']['haveFlashNotifications'] = true; askbot['data']['activeTab'] = 'questions'; askbot['settings']['csrfCookieName'] = 'csrftoken'; askbot['data']['searchUrl'] = ''; /*<![CDATA[*/ $('.mceStatusbar').remove();//a hack to remove the tinyMCE status bar$(document).ready(function(){ // focus input on the search bar endcomment var activeTab = askbot['data']['activeTab']; if (inArray(activeTab, ['users', 'questions', 'tags', 'badges'])) { var searchInput = $('#keywords'); } else if (activeTab === 'ask') { var searchInput =$('#id_title'); } else { var searchInput = undefined; animateHashes(); } if (searchInput) { searchInput.focus(); putCursorAtEnd(searchInput); } var haveFullTextSearchTab = inArray(activeTab, ['questions', 'badges', 'ask']); var haveUserProfilePage = $('body').hasClass('user-profile-page'); if ((haveUserProfilePage || haveFullTextSearchTab) && searchInput && searchInput.length) { var search = new FullTextSearch(); askbot['controllers'] = askbot['controllers'] || {}; askbot['controllers']['fullTextSearch'] = search; search.setSearchUrl(askbot['data']['searchUrl']); if (activeTab === 'ask') { search.setAskButtonEnabled(false); } search.decorate(searchInput); } else if (activeTab === 'tags') { var search = new TagSearch(); search.decorate(searchInput); } if (askbot['data']['userIsAdminOrMod']) {$('body').addClass('admin'); } if (askbot['settings']['groupsEnabled']) { askbot['urls']['add_group'] = "/s/add-group/"; var group_dropdown = new GroupDropdown(); $('.groups-dropdown').append(group_dropdown.getElement()); } var userRep =$('#userToolsNav .reputation'); if (userRep.length) { var showPermsTrigger = new ShowPermsTrigger(); showPermsTrigger.decorate(userRep); } }); if (askbot['data']['haveFlashNotifications']) { $('#validate_email_alert').click(function(){notify.close(true)}) notify.show(); } var langNav =$('.lang-nav'); if (langNav.length) { var nav = new LangNav(); nav.decorate(langNav); } /*]]>*/ //todo - take this out into .js file $(document).ready(function(){$('div.revision div[id^=rev-header-]').bind('click', function(){ var revId = this.id.substr(11); toggleRev(revId); }); lanai.highlightSyntax(); }); function toggleRev(id) { var arrow = $("#rev-arrow-" + id); var visible = arrow.attr("src").indexOf("hide") > -1; if (visible) { var image_path = '/m/default/media/images/expander-arrow-show.gif?v=6'; } else { var image_path = '/m/default/media/images/expander-arrow-hide.gif?v=6'; } image_path = image_path + "?v=6"; arrow.attr("src", image_path);$("#rev-body-" + id).slideToggle("fast"); } for (url_name in askbot['urls']){ askbot['urls'][url_name] = cleanUrl(askbot['urls'][url_name]); }