Python iOS摄像头输出向左旋转90度

我将按照本教程构建一个简单的交通标志识别深度学习应用程序

我制作了一个自己的模型，并在该存储库中使用该模型进行了尝试：

当我在iPhone上的xcode上运行应用程序时，只有当交通标志向右旋转90度时，它才能识别。 我怎样才能解决这个问题

这是我的AppDelegate.swift：

    //
//  AppDelegate.swift
//  trafficsign
//
//  Created by administrator on 2020. 11. 11..
//  Copyright © 2020. administrator. All rights reserved.
//

import UIKit

@UIApplicationMain
class AppDelegate: UIResponder, UIApplicationDelegate {

    var window: UIWindow?

    func application(_ application: UIApplication, didFinishLaunchingWithOptions launchOptions: [UIApplication.LaunchOptionsKey: Any]?) -> Bool {
        // Override point for customization after application launch.
        // Override point for customization after application launch.
        
        window = UIWindow()
        window?.makeKeyAndVisible()
        let vc = ViewController()
        
        window?.rootViewController = vc
        return true
    }

    


}

    //
//  SceneDelegate.swift
//  trafficsign
//
//  Created by administrator on 2020. 11. 11..
//  Copyright © 2020. administrator. All rights reserved.
//

import UIKit

class SceneDelegate: UIResponder, UIWindowSceneDelegate {

    var window: UIWindow?


    func scene(_ scene: UIScene, willConnectTo session: UISceneSession, options connectionOptions: UIScene.ConnectionOptions) {
        // Use this method to optionally configure and attach the UIWindow `window` to the provided UIWindowScene `scene`.
        // If using a storyboard, the `window` property will automatically be initialized and attached to the scene.
        // This delegate does not imply the connecting scene or session are new (see `application:configurationForConnectingSceneSession` instead).
        guard let windowScene = (scene as? UIWindowScene) else { return }
        window = UIWindow(windowScene: windowScene)
        window?.rootViewController = ViewController()
        window?.makeKeyAndVisible()
    }

    func sceneDidDisconnect(_ scene: UIScene) {
        // Called as the scene is being released by the system.
        // This occurs shortly after the scene enters the background, or when its session is discarded.
        // Release any resources associated with this scene that can be re-created the next time the scene connects.
        // The scene may re-connect later, as its session was not neccessarily discarded (see `application:didDiscardSceneSessions` instead).
    }

    func sceneDidBecomeActive(_ scene: UIScene) {
        // Called when the scene has moved from an inactive state to an active state.
        // Use this method to restart any tasks that were paused (or not yet started) when the scene was inactive.
    }

    func sceneWillResignActive(_ scene: UIScene) {
        // Called when the scene will move from an active state to an inactive state.
        // This may occur due to temporary interruptions (ex. an incoming phone call).
    }

    func sceneWillEnterForeground(_ scene: UIScene) {
        // Called as the scene transitions from the background to the foreground.
        // Use this method to undo the changes made on entering the background.
    }

    func sceneDidEnterBackground(_ scene: UIScene) {
        // Called as the scene transitions from the foreground to the background.
        // Use this method to save data, release shared resources, and store enough scene-specific state information
        // to restore the scene back to its current state.
    }


}

斯威夫特：

    //
//  AppDelegate.swift
//  trafficsign
//
//  Created by administrator on 2020. 11. 11..
//  Copyright © 2020. administrator. All rights reserved.
//

import UIKit

@UIApplicationMain
class AppDelegate: UIResponder, UIApplicationDelegate {

    var window: UIWindow?

    func application(_ application: UIApplication, didFinishLaunchingWithOptions launchOptions: [UIApplication.LaunchOptionsKey: Any]?) -> Bool {
        // Override point for customization after application launch.
        // Override point for customization after application launch.
        
        window = UIWindow()
        window?.makeKeyAndVisible()
        let vc = ViewController()
        
        window?.rootViewController = vc
        return true
    }

    


}

    //
//  SceneDelegate.swift
//  trafficsign
//
//  Created by administrator on 2020. 11. 11..
//  Copyright © 2020. administrator. All rights reserved.
//

import UIKit

class SceneDelegate: UIResponder, UIWindowSceneDelegate {

    var window: UIWindow?


    func scene(_ scene: UIScene, willConnectTo session: UISceneSession, options connectionOptions: UIScene.ConnectionOptions) {
        // Use this method to optionally configure and attach the UIWindow `window` to the provided UIWindowScene `scene`.
        // If using a storyboard, the `window` property will automatically be initialized and attached to the scene.
        // This delegate does not imply the connecting scene or session are new (see `application:configurationForConnectingSceneSession` instead).
        guard let windowScene = (scene as? UIWindowScene) else { return }
        window = UIWindow(windowScene: windowScene)
        window?.rootViewController = ViewController()
        window?.makeKeyAndVisible()
    }

    func sceneDidDisconnect(_ scene: UIScene) {
        // Called as the scene is being released by the system.
        // This occurs shortly after the scene enters the background, or when its session is discarded.
        // Release any resources associated with this scene that can be re-created the next time the scene connects.
        // The scene may re-connect later, as its session was not neccessarily discarded (see `application:didDiscardSceneSessions` instead).
    }

    func sceneDidBecomeActive(_ scene: UIScene) {
        // Called when the scene has moved from an inactive state to an active state.
        // Use this method to restart any tasks that were paused (or not yet started) when the scene was inactive.
    }

    func sceneWillResignActive(_ scene: UIScene) {
        // Called when the scene will move from an active state to an inactive state.
        // This may occur due to temporary interruptions (ex. an incoming phone call).
    }

    func sceneWillEnterForeground(_ scene: UIScene) {
        // Called as the scene transitions from the background to the foreground.
        // Use this method to undo the changes made on entering the background.
    }

    func sceneDidEnterBackground(_ scene: UIScene) {
        // Called as the scene transitions from the foreground to the background.
        // Use this method to save data, release shared resources, and store enough scene-specific state information
        // to restore the scene back to its current state.
    }


}

最重要的是我的ViewController.swift：

    //
//  ViewController.swift
//  trafficsign
//
//  Created by administrator on 2020. 11. 11..
//  Copyright © 2020. administrator. All rights reserved.
//

import UIKit
import AVFoundation
import Vision

class ViewController: UIViewController, AVCaptureVideoDataOutputSampleBufferDelegate {
    let label: UILabel = {
        let label = UILabel()
        label.textColor = .white
        label.translatesAutoresizingMaskIntoConstraints = false
        label.text = "Label"
        label.font = label.font.withSize(30)
        return label
    }()
    
    override func viewDidLoad() {
        super.viewDidLoad()
        
        setupCaptureSession()
        
        view.addSubview(label)
        setupLabel()
    }
    
    override func didReceiveMemoryWarning() {
        // call the parent function
        super.didReceiveMemoryWarning()
        
        // Dispose of any resources that can be recreated.
    }
    
    func setupCaptureSession() {
        // create a new capture session
        let captureSession = AVCaptureSession()
        
        // find the available cameras
        let availableDevices = AVCaptureDevice.DiscoverySession(deviceTypes: [.builtInWideAngleCamera], mediaType: AVMediaType.video, position: .back).devices
        
        do {
            // select a camera
            if let captureDevice = availableDevices.first {
                captureSession.addInput(try AVCaptureDeviceInput(device: captureDevice))
            }
        } catch {
            // print an error if the camera is not available
            print(error.localizedDescription)
        }
        
        // setup the video output to the screen and add output to our capture session
        let captureOutput = AVCaptureVideoDataOutput()
        captureSession.addOutput(captureOutput)
        let previewLayer = AVCaptureVideoPreviewLayer(session: captureSession)
        previewLayer.frame = view.frame
        view.layer.addSublayer(previewLayer)
        
        // buffer the video and start the capture session
        captureOutput.setSampleBufferDelegate(self, queue: DispatchQueue(label: "videoQueue"))
        captureSession.startRunning()
        
//        // creates a new capture session
//        let captureSession = AVCaptureSession()
//
//        // search for available capture devices
//        let availableDevices = AVCaptureDevice.DiscoverySession(deviceTypes: [.builtInWideAngleCamera], mediaType: AVMediaType.video, position: .back).devices
//
//        // get capture device, add device input to capture session
//        do {
//            if let captureDevice = availableDevices.first {
//                captureSession.addInput(try AVCaptureDeviceInput(device: captureDevice))
//            }
//        } catch {
//            print(error.localizedDescription)
//        }
//
//        // setup output, add output to capture session
//        let captureOutput = AVCaptureVideoDataOutput()
//        captureSession.addOutput(captureOutput)
//
//        captureOutput.setSampleBufferDelegate(self, queue: DispatchQueue(label: "videoQueue"))
//
//        let previewLayer = AVCaptureVideoPreviewLayer(session: captureSession)
//        previewLayer.frame = view.frame
//        previewLayer.videoGravity = .resizeAspectFill
//        view.layer.addSublayer(previewLayer)
//
//        captureSession.startRunning()
    }
    
    // called everytime a frame is captured
    func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
        // load our CoreML Pokedex model
        guard let model = try? VNCoreMLModel(for: model_squeezeNet_TSR().model) else { return }
        // run an inference with CoreML
        let request = VNCoreMLRequest(model: model) { (finishedRequest, error) in
            // grab the inference results
            guard let results = finishedRequest.results as? [VNClassificationObservation] else { return }
            
            // grab the highest confidence result
            guard let Observation = results.first else { return }
            
            // create the label text components
            let predclass = "\(Observation.identifier)"
            let predconfidence = String(format: "%.02f%", Observation.confidence * 100)
            // set the label text
            DispatchQueue.main.async(execute: {
                self.label.text = "\(predclass) \(predconfidence)"
            })
        }
        
        // create a Core Video pixel buffer which is an image buffer that holds pixels in main memory
        // Applications generating frames, compressing or decompressing video, or using Core Image
        // can all make use of Core Video pixel buffers
        guard let pixelBuffer: CVPixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else { return }
        
        // execute the request
        try? VNImageRequestHandler(cvPixelBuffer: pixelBuffer, options: [:]).perform([request])
        
//        guard let model = try? VNCoreMLModel(for: model_squeezeNet_TSR().model) else { return }
//        let request = VNCoreMLRequest(model: model) { (finishedRequest, error) in
//            guard let results = finishedRequest.results as? [VNClassificationObservation] else { return }
//            guard let Observation = results.first else { return }
//
//            DispatchQueue.main.async(execute: {
//                self.label.text = "\(Observation.identifier)"
//                print(Observation.confidence)
//            })
//        }
//        guard let pixelBuffer: CVPixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else { return }
//        // executes request
//        try? VNImageRequestHandler(cvPixelBuffer: pixelBuffer, options: [:]).perform([request])
    }
    
    func setupLabel() {
        label.centerXAnchor.constraint(equalTo: view.centerXAnchor).isActive = true
        label.bottomAnchor.constraint(equalTo: view.bottomAnchor, constant: -50).isActive = true
    }
}

---

来自摄影机的图像始终以横向方向显示

您可以通过告诉视频连接改用纵向，或自己旋转图像来修复此问题，但最简单的解决方案是将方向传递到VNImageRequestHandler

要么是

.landscapeLeft

要么

.landscapeRight

，我总是忘记哪个是正确的

---

还请注意，每次从视频捕获接收帧时，不应创建

VNCoreMLModel

和

VNCoreMLRequest

实例。将它们分配一次并重新使用。

谢谢您的回答。与python相比，我对swift更不熟悉。请告诉我，我可以在哪里设置方向，我应该插入什么代码，在哪里？我应该在哪里创建VNCoreMLModel和VNCoreMLRequest？（而是每次都创建它们。）我发现了这个：如果我尝试键入这个：尝试？VNImageRequestHandler（cvPixelBuffer:pixelBuffer，方向：.landscapeRight，选项：[：]）。执行（[request]），然后它说没有名为.landscapeRight的属性。只有左和右。好的，所以解决办法是：试试？VNImageRequestHandler（cvPixelBuffer:pixelBuffer，方向：。右，选项：[：]）.perform（[request]）奇怪的是，它似乎对.left和.right都或多或少起作用。我如何知道哪一个是正确的？您可以使用的CheckInputImage项目来试验Vision如何查看图像。把这个模型放到你自己的应用程序中，在UIImageView中画出它输出的图像，你就会知道了。似乎是正确的。否则，它只能识别颠倒的图像。我先用一个“优先道路”的标志试了一下，同样是颠倒过来的