Imshow not able to update image when using Haar Cascade opencv -


i had used haar-cascade detect human on thermal image in raspberry pi. in order improve model performance, had used 2000 of images train model. model size 201kb. 60kb , 89kb when trained model less no. of images. use 201kb model , detect human , display on screen using imshow, imshow doesnot update image in real time, there of delay or imshow gets hangs. works fine 60kb , 89kb model. tried using opengl display image in real time no help.

what should make output display similar real-time using imshow?

since runs fine smaller models, imshow not bottleneck. detectmultiscalewith bigger model takes time. can try either

  1. reduce number of stages in model
  2. resize input frame
  3. adjust minsize , maxsize of detectmultiscale

Comments

Popular posts from this blog

Command prompt result in label. Python 2.7 -

javascript - How do I use URL parameters to change link href on page? -

amazon web services - AWS Route53 Trying To Get Site To Resolve To www -