通过 AVMutableVideoComposition 覆盖静态文本

Question

在 iOS 版 Swift 中，我有一个

AVURLAsset

数组。我通过一个函数将其传递，将视频资源拼接/合并到一个最终视频中。对于每个视频，我的目标是覆盖框架中居中的文本。

当我播放输出的视频时，视频资源正确合并，但我无法理解为什么没有文本叠加。我尝试遵循“现有答案”，但无济于事。任何指导将不胜感激..

func merge(videos: [AVURLAsset], completion: @escaping (_ url: URL, _ asset: AVAssetExportSession)->()) {
let videoComposition = AVMutableComposition()
var lastTime: CMTime = .zero

var count = 0
var maxVideoSize = CGSize.zero // For determining the maximum video size

guard let videoCompositionTrack = videoComposition.addMutableTrack(withMediaType: .video, preferredTrackID: Int32(kCMPersistentTrackID_Invalid)) else { return }
guard let audioCompositionTrack = videoComposition.addMutableTrack(withMediaType: .audio, preferredTrackID: Int32(kCMPersistentTrackID_Invalid)) else { return }

let mainComposition = AVMutableVideoComposition()
var parentLayers = [CALayer]() // To hold all individual parent layers

for video in videos {
    
    if let videoTrack = video.tracks(withMediaType: .video)[safe: 0] {
        
        videoCompositionTrack.preferredTransform = videoTrack.preferredTransform
        
        do {
            try videoCompositionTrack.insertTimeRange(CMTimeRangeMake(start: .zero, duration: video.duration), of: videoTrack, at: lastTime)
            
            if let audioTrack = video.tracks(withMediaType: .audio)[safe: 0] {
                try audioCompositionTrack.insertTimeRange(CMTimeRangeMake(start: .zero, duration: video.duration), of: audioTrack, at: lastTime)
            }
            lastTime = CMTimeAdd(lastTime, video.duration)

            // Obtain video dimensions and update max size if necessary
            let videoSize = videoTrack.naturalSize.applying(videoTrack.preferredTransform)
            let videoRect = CGRect(x: 0, y: 0, width: abs(videoSize.width), height: abs(videoSize.height))
            if videoRect.width > maxVideoSize.width {
                maxVideoSize.width = videoRect.width
            }
            if videoRect.height > maxVideoSize.height {
                maxVideoSize.height = videoRect.height
            }

            // Create and configure the text layer for this segment
            let textLayer = CATextLayer()
            textLayer.string = "TESTING"
            textLayer.foregroundColor = UIColor.white.cgColor
            textLayer.backgroundColor = UIColor.clear.cgColor
            textLayer.fontSize = 100
            textLayer.shadowOpacity = 0.5
            textLayer.alignmentMode = .center
            textLayer.contentsScale = UIScreen.main.scale // Ensures text is sharp
            textLayer.isWrapped = true // Allows text wrapping if needed

            // Calculate frame for centrally aligned text
            let textHeight: CGFloat = 120 // Adjust as needed
            let textWidth: CGFloat = videoRect.width // Padding from edges
            let xPos = (videoRect.width - textWidth) / 2
            let yPos = (videoRect.height - textHeight) / 2
            textLayer.frame = CGRect(x: xPos, y: yPos, width: textWidth, height: textHeight)
            print(textLayer.frame)

            // Create a parent layer for video and text
            let parentLayer = CALayer()
            let videoLayer = CALayer()
            parentLayer.frame = videoRect
            videoLayer.frame = videoRect
            textLayer.zPosition = 1 // Ensuring text layer is on top
            parentLayer.addSublayer(videoLayer)
            parentLayer.addSublayer(textLayer)
            parentLayers.append(parentLayer) // Add to array

            // Add parent layer to video composition
            let videoCompositionInstruction = AVMutableVideoCompositionInstruction()
            videoCompositionInstruction.timeRange = CMTimeRangeMake(start: .zero, duration: video.duration)
            let layerInstruction = AVMutableVideoCompositionLayerInstruction(assetTrack: videoTrack)
            videoCompositionInstruction.layerInstructions = [layerInstruction]
            mainComposition.instructions.append(videoCompositionInstruction)

            count += 1
        } catch {
            print("Failed to insert track")
            return
        }
    }
}

let mainParentLayer = CALayer()
mainParentLayer.frame = CGRect(x: 0, y: 0, width: maxVideoSize.width, height: maxVideoSize.height)
for layer in parentLayers {
    mainParentLayer.addSublayer(layer)
}

// Set the renderSize and frameDuration of the mainComposition
mainComposition.renderSize = maxVideoSize
mainComposition.frameDuration = CMTime(value: 1, timescale: 30) // Assuming 30 fps
mainComposition.animationTool = AVVideoCompositionCoreAnimationTool(postProcessingAsVideoLayer: mainParentLayer, in: mainParentLayer)

let outputUrl = NSURL.fileURL(withPath: NSTemporaryDirectory() + "mergedVid" + ".mp4")

guard let exporter = AVAssetExportSession(asset: videoComposition, presetName: AVAssetExportPresetHighestQuality) else { return }

exporter.videoComposition = mainComposition
exporter.outputURL = outputUrl
exporter.outputFileType = .mp4
exporter.shouldOptimizeForNetworkUse = true

exporter.exportAsynchronously {
    DispatchQueue.main.async {
        if let outputUrl = exporter.outputURL, exporter.status == .completed {
            completion(outputUrl, exporter)
        } else if let error = exporter.error {
            print("Export failed: \(error.localizedDescription)")
        }
    }
}

play(video: exporter.asset)
}

Answer 1

AVVideoCompositionCoreAnimationTool

 未正确配置为在视频上合成这些层。

您应该创建一个主视频图层 (

mainVideoLayer

) 并将其添加到主父图层 (

mainParentLayer

)。然后，将每个视频的文本图层添加到

mainParentLayer

。这确保了适当的层次结构，其中文本叠加正确定位在视频内容上。

并将 

AVVideoCompositionCoreAnimationTool
配置为要处理的视频层，将

mainVideoLayer

作为动画层。确保每个mainParentLayer

正确跨越其相应视频片段的整个持续时间。这对于无缝播放和文本的正确叠加应该很重要。

您的

AVMutableVideoCompositionInstruction功能将是（仅限相关摘录）：

merge