ObjectDetection | Object detection example using CNTK and Python | Computer Vision library

I'm learning image detection and python writing a bot for a 2d game. There are certain targets we want to attack and certain targets we want to avoid. One target is displayed on the screen at a time out of a pool of 100 and you click next or attack depending on what you want to do. In doing this you're able to cycle through targets until you find one you want to attack. My code currently checks to see if it finds one of 24 different targets we want to avoid, if it does it avoids that target. Otherwise, it attacks that target.

At the moment my code:

I'm learning OpenCV & Python by writing a bot for a 2d spaceship game.

The basic principle is there are certain targets my spaceship can defeat and certain spaceships it cannot defeat. One target is displayed on the screen at a time and you click either next or attack depending on what you want to do. In doing this you're able to cycle through targets until you find one you want to attack.

At the moment my code:

1. Loads images of ships it cannot defeat into an numpy array
2. Some pyautigui interactions to skip through menus
3. Checks the numpy array to determine if it wants to attack or skip the target it's been given
4. Clicks attack or skip with pyautogui

This all works correctly and the bot happily searches away and either clicks skip or attack.

My issue:

The names of the images being loaded are human-readable e.g. Ship 1.jpg, Ship 2.jpg, Ship 3.jpg When I load them into the numpy array they lose their human-readable component.

My Question:

I want to be able to log what was attacked to refine the detection, at the moment I'm able to output the actual array array([[106, 106, 106, ..., 42, 41, 42], but I can't seem to figure out how to keep the human-readable element. How can I keep the human-readable element?

I'm loading the images like this:

I'm using PILs ImageGrab function to capture an application window in real-time for image detection with OpenCV. I've managed to scale the captured window down to increase the speed of image detection. However, I'm getting a number of false positives I can't seem to avoid. I actually only need to capture a small section of the window 761 34 1142 68

I am new to ML and am trying to make inferences using the YoloV5 model from a C# program. I am aware of the github port, but would like to use torch instead of ML.NET. I found PythonNET nuget package, and this code is working:

I am currently using android-demo-app/ObjectDetection/ On Temi Robot, the preloaded images are working so far but when I press "live" to go to live object detection screen, it is rotated 90 degrees to the right.

Temi robot only have a front facing camera on the same side of the screen.

I have tried changing textureView.setTransform() imageAnalysisConfig.Builder().setTargetRotation() imageAnalysis.setTargetRotation() but to no avail

Also tried changing AndroidManifest.xml screenOrientation under activity tag to fullSenor or Landscape but nothing changed.

I have been looking up and down on the Android Developer CameraX page for an answer first link second link but I can't find any. Maybe I am not smart enough to find the solution here.

Any help is much appreciated!

AbstactCameraXActivity.java

I want my application to say a voice message when I press the button "btnObjectDetection". The application does an object detection task, and I want a welcome message. Currently, the application compiles and runs without problem but does not say anything from the voice message. Please help me :( This is my code:

activity_main.xml

I've trained Yolov5s model in colab.research env. After training I've moved best.pt to main yolov5 directory and renamed file to yolov5s.pt.

After calling export.py i got error listed below

Summary/TL;DR: ML Object Detection application is unable to detect objects because images aren't being acquired by analyze() method.

I'm currently working on a mobile application using CameraX and Google ML Kit written in Java. The purpose of the application is to detect objects with a real time camera preview. I implemented ML Kit using this guide aptly titled "Detect and track objects with ML Kit on Android" (base model option) to detect objects in successive frames within the application.

However, upon running the application, it launches on my device and the camera preview continues to work but the application does not carry out its intended effect of actually detecting objects and displaying it on my screen. To attempt to resolve this, I had found this StackOverflow answer that very closely resembles this issue. To my dismay, the user had built their application using a custom model (tflite). This differs from mine as I am using the base model. According to my research, this uses the ML Kit's on-device's object detection. The code being applied is restricted to what is present within the aforementioned documentation. Since my IDE (Android Studio) does not display any errors within the syntax, I am unsure as to why any object detection does not appear to be present on my application. Displayed below is the necessary code that had been used:

I am trying to setup an ImageAnalyzer with my Android app so I can run object classification using Google's ML Kit API. The issue I am currently facing, as the title suggests, is constantly seeing the error "Failed to initialize detector".

I've reread this tutorial about three times now and followed this post about someone facing the same error (although for a different reason) to no avail. I've also made sure everything with the CameraX API (except the ImageAnalyzer code that I will show in a second) works as expected.

As mentioned in the ML Kit documentation, here is the code I have regarding setting up a LocalModel, a CustomObjectDetectorOptions, and an ObjectDetector: