How to use the Object Detection Bounding Box in a decision condition to turn on the LED on Raspberry Pi using C++ OpenCV? -

-

I am using OpenCV 2.4.8 to create an application that will detect guns. The application will be posted on Raspberry P. An LED / buzzer is also connected to Raspberry P. If the gun is detected, then the LED / buzzer should be turned on according to certain conditions. I have attached the relevant code. The problem is how to tell the code whether the gun is detected or not? I mean, the traced gun has been shown by a bounding box. Now, how to use that bounding box in IF-condition? I have commented on the desired lines in the code, like what I really want to do, can someone guide me how to do it? Any help is highly appreciated! Thank you.
This is my code snippet: 

 for  (;;) {cap.retrieve (frame); Caps & gt; & Gt; Frame; Std :: vector & lt; Rect & gt; Guns; Mat frame_grey; CvtColor (frame, frame_grey, COLOR_BGR2GRAY); Equalize (frame_grey, frame_grey); // Address Guns gun_cascade.detectMultiScale (frame_gray, guns, 1.1, 2, 0 | CASCADE_SCALE_IMAGE, size (30, 30)); // Set Interest Area cv :: Rect roi_b; CV :: rectangle roi_c; CV :: ReadBox; Size_ty IC = 0; // IC is an index of the current element, AC = 0; // The current element is the area of ​​size_t ib = 0; //IiB's largest element is int ab = 0; // AB (ic = 0; ic & lt; guns.size (IC ++) // Re-enter all existing elements (detected guns) {roi_c.x = gun [IC] .x; Roi_c.y = gun [IC] .y; Roi_c.width = (gun [IC] .Wide); Roi_c.height = (gun [IC]. Highlight); AC = roi_c.width * roi_c.height; // current Get the area of ​​the element (detection gun) roi_b.x = gun [ib] .x; Roi_b.y = gun [ib] .y; Roi_b.width = (gun [ib] wide); Roi_b.height = (Gun [ib]. Hi); ab = roi_b.width * roi_b.height; // Get the area of ​​the largest element, initially Is similar to the "present" element if (AC> AB) {IB = IC; Roi_b.x = gun [ib] .x; Roi_b.y = gun [ib] .y; Roi_b.width = (gun [ Ib] wide; roi_b.height = (gun [ib] .hite);} point pt1 (gun [ic] .x, gun [ic].); // display guns on main window in display- cameras //www.bbox.com/cvRect (roi_b.x) from the live stream point pt2 (gun (ic) .x + gun [ic] .high), (guns [ii] .i + gun [ic] Roi_b.y, roi_b.width, roi_b.height); // int counter = 0; Rectangle (frame, pt1, pt2, scalar (0, 0, 255), 2, 8, 0); PutText (frame, "Gun Detected!", Pt1, FONT_HERSHEY_COMPLEX_SMALL, 0.8, cvScalar (0,250,250), 1, CV_AA); // if (gun is detected) // counter = counter + 1; / * If (counter> 5) {Turn on the LED of Raspberry P; Counter = 0; } * //} imshow for the end loop ("original", frame); If (wait (30)> ==) break; } // the end of the external for loop returns 0; } // main main    
 
 
 You have a very clear code that can be brought down For single-line statements.  
  ab = 0; (IC = 0; IC & lt; guns size (IC ++) {roi_c = guns [i]; if (roi_c.area ()> ab) {roi_b = roi_c; ab = roi_c.area (); } Rectangle (frame, ROIIC, scalar (0, 0, 255), 2, 8, 0);}   
 If you want to check that  at least  If a gun is detected, then you can type:  if (guns.size ()> gt0) {..}  If you want to check whether the biggest gun with some threshold You can go with something like  (roi_b.area () & gt; some_threshold) .  
 Hope this answer.

Comments

Post a Comment

Popular posts from this blog

java - ImportError: No module named py4j.java_gateway -

-
I'm trying to call the Python using the Java program py4j . I've been installing the plug-in Eclipse and test name Piidvi project. I'm trying to execute the following part of the code found on py4j webpage: Import from py4j.java_gateway to JavaGateway, java_import gateway = JavaGateway () jvm = gateway.jvm java_import (jvm, '' Org.eclipse Kkorkrisorsej. * ") Vrkspes_rut = Jvankresourkesplginkgetvrkspas (). GetRoot (Gateway .help (workspace_root, '* Projects *') project_names = [project.getName () (for projects workpace_root.getProjects))] print (Projekt_nam) But I There is an error in import. I have checked that the P4JJ is present in the Jar Eclipse plugin directory. Can anyone help please? I had to install the py4j application
Read more

python - Receiving "KeyError" after decoding json result from url -

-
I am new to Python I am trying to parse JSON result from a URL. Basically, I was using the following: response = urllib.request.urlopen (url) json_obj = json.load (response) It should be a stroke "str 'not' bytes' in the lines of a given" JSON object, so after searching on the StackoverView Flo, I decode the response in this way: F = urllib.request.urlopen (Url) charset = f.info (). Get_param ('charset', 'utf8') data = f.read () decoded = json.loads (data.decode (charset)) If I print "decode" I is as follows: { 'link': { 'summary data': 'https: // localhost / piwebapi / streams / p0_7qHaW4UHU-RlCaz8tpasAAQAAAAU0hJTExNQU42NDIwXFNJTlVTT0lE / summary' 'value': 'https: // localhost / Piwebapi / streams / P0_7qHaW4UHU-RlCaz8tpasAAQAAAAU0hJTExNQU42NDIwXFNJTlVTT0lE / price ',' InterpolatedData ':' https: // localhost / Piwebapi / streams / P0_7qHaW4UHU-RlCaz8tpasAAQAAAAU0hJTE...
Read more

.net - Creating a new Queue Manager and Queue in Websphere MQ (using C#) -

-
"itemprop =" text "> I am writing applications that use WebSphere MQ to send messages. My unittests (for flow), I want to verify that I have put the correct message on the response queue. I am trying to figure out how to do this. My main obstacle is that I think it might be scary to clear the queue before running in my queue because the same queue can be used by other applications, I thought a decent solution would be a new line The manager will remove the queue for my solidarity and after using it. So my question is: Is it possible to use C # by using queue manager and queue? After the For future reference and future people, who want to make queues. I thought how to make and remove IBM MQ QE (not quenhers) with PCM messaging. It is not very simple, but it can be done. We have implemented it in a library and it is being used to create and delete commands before and after integration tests. The most important part of the code in this library is shown in the...
Read more