How to add cover picture to audio and video?

This is my code, but it doesn't work. The log is at the en. log -> Stream #0:2: Video: mjpeg, yuvj444p, 1920x1080, q=2-31, 400 kb/s, 30 fps, 30 tbn, 30 tbc (attached pic)

        FFmpegFrameRecorderPlus recorder = new FFmpegFrameRecorderPlus("D:\\video\\fengmian\\111.mp4", 1920, 1080);
	recorder.setVideoCodec(avcodec.AV_CODEC_ID_H264);
	recorder.setPixelFormat(avutil.AV_PIX_FMT_YUV420P);
	recorder.setFrameRate(25);
	recorder.setFormat("mp4");
	recorder.setAudioOption("crf", "0");
	recorder.setAudioQuality(0);
	recorder.setAudioBitrate(192000);
	recorder.setSampleRate(44100);
	recorder.setAudioChannels(2);
	recorder.setAudioCodec(avcodec.AV_CODEC_ID_MP3);
	recorder.start();
	try {
		BufferedImage read = ImageIO.read(new File("D:\\video\\3.jpg"));
		Java2DFrameConverter converter = new Java2DFrameConverter();
		Frame frame = converter.getFrame(read);
		for (int i = 0; i < 250; i++) {
			recorder.record(frame);
		}

		String filename = recorder.getFilename();
		AVFormatContext oc = recorder.getAVFormatContext();
		AVStream video_st = avformat_new_stream(oc, null);
		System.out.println("filename: " + recorder.getFilename() + ", index: " + video_st.index());
		
		read = ImageIO.read(new File("D:\\video\\1.jpg"));
		converter = new Java2DFrameConverter();
		frame = converter.getFrame(read);
		int width = frame.imageWidth;
		int height = frame.imageHeight;
		int depth = frame.imageDepth;
		int stride = frame.imageStride;
		BytePointer data = new BytePointer((ByteBuffer) frame.image[0]).position(0); // new BytePointer((ByteBuffer)image[0]).position(0)
								   
		AVBufferRef avBufferRef = new AVBufferRef(data);
		video_st.attached_pic().buf(avBufferRef);
		video_st.attached_pic().data(avBufferRef.data());
		video_st.attached_pic().stream_index(video_st.index());
		video_st.attached_pic().flags(avcodec.AV_CODEC_FLAG_GLOBAL_HEADER);
		video_st.disposition(avformat.AV_DISPOSITION_ATTACHED_PIC);
		video_st.codecpar().codec_type(avutil.AVMEDIA_TYPE_VIDEO);
		video_st.codecpar().codec_id(avcodec.AV_CODEC_ID_MJPEG);

		AVCodec video_codec;
		if ((video_codec = avcodec_find_encoder(avcodec.AV_CODEC_ID_MJPEG)) == null) {
			throw new Exception("avcodec_find_encoder() error: Video codec not found.");
		}
		AVCodecContext video_c;
		if ((video_c = avcodec_alloc_context3(video_codec)) == null) {
			throw new Exception("avcodec_alloc_context3() error: Could not allocate video encoding context.");
		}
		
        video_c.codec_id(video_codec.id());
		video_c.codec_type(video_codec.type());
        video_c.bit_rate(400000);
        video_c.width(1920);
        video_c.height(1080);
        video_c.pix_fmt(avutil.AV_PIX_FMT_YUVJ444P);

		video_c.profile(AVCodecContext.FF_PROFILE_H264_CONSTRAINED_BASELINE);
		video_c.flags(video_c.flags() | AV_CODEC_FLAG_GLOBAL_HEADER);
		video_c.thread_count(0);
		
		int ret = -1;
        if ((ret = avcodec_parameters_from_context(video_st.codecpar(), video_c)) < 0) {
            throw new Exception("avcodec_parameters_from_context() error: Could not copy the video stream parameters.");
        }
		
		AVRational frame_rate = av_d2q(30, 1001000);
		AVRational time_base = avutil.av_inv_q(frame_rate);
		video_c.time_base(time_base);
		
		video_st.time_base(time_base);
		video_st.avg_frame_rate(frame_rate);
		video_st.codec().time_base(time_base);

		AVDictionary options = new AVDictionary(null);
        avcodec_open2(video_c, video_codec, options);
        av_dict_free(options);
        
        AVFrame picture = null, tmp_picture = null;
		if ((picture = av_frame_alloc()) == null) {
			throw new Exception("av_frame_alloc() error: Could not allocate picture.");
		}
		picture.pts(0); 
		if ((tmp_picture = av_frame_alloc()) == null) {
			throw new Exception("av_frame_alloc() error: Could not allocate temporary picture.");
		}
        
		BytePointer picture_buf = null;
		int size = av_image_get_buffer_size(avutil.AV_PIX_FMT_YUVJ444P, 1920, 1080, 1);
		if ((picture_buf = new BytePointer(av_malloc(size))).isNull()) {
			throw new Exception("av_malloc() error: Could not allocate picture buffer.");
		}
		
        AVDictionary metadata = new AVDictionary(null);
        av_dict_set(metadata, "my_title", "my_value", 0);
        av_dict_set(metadata, "my_title1", "my_value1", 0);
        video_st.metadata(metadata);
		
		int step = stride * Math.abs(depth) / 8;
		int pixelFormat = avutil.AV_PIX_FMT_YUVJ444P;

        av_image_fill_arrays(new PointerPointer(tmp_picture), tmp_picture.linesize(), data, pixelFormat, width, height, 1);
        av_image_fill_arrays(new PointerPointer(picture), picture.linesize(), picture_buf, video_c.pix_fmt(), video_c.width(), video_c.height(), 1);
       
		tmp_picture.linesize(0, step);
        tmp_picture.format(pixelFormat);
        tmp_picture.width(width);
        tmp_picture.height(height);
        
		picture.format(pixelFormat);
		picture.width(1920);
		picture.height(1080);
        
		SwsContext img_convert_ctx = null;
		img_convert_ctx = sws_getCachedContext(img_convert_ctx, width, height, pixelFormat, 1920, 1080, video_c.pix_fmt(), SWS_BILINEAR, null, null, (DoublePointer) null);
		if (img_convert_ctx == null) {
			throw new Exception("sws_getCachedContext() error: Cannot initialize the conversion context.");
		}
		sws_scale(img_convert_ctx, new PointerPointer(tmp_picture), tmp_picture.linesize(), 0, height, new PointerPointer(picture), picture.linesize());
		
        AVPacket video_pkt = new AVPacket();
		av_init_packet(video_pkt);
		video_pkt.data(data);
		video_pkt.size((int)data.capacity());
		video_pkt.pos(-1);
		picture.quality(video_c.global_quality());
		
		int[] got_video_packet = new int[1];
		if ((ret = avcodec_encode_video2(video_c, video_pkt, picture, got_video_packet)) < 0) {
			throw new Exception("avcodec_encode_video2() error " + ret + ": Could not encode video packet.");
		}
		
		if (got_video_packet[0] != 0) {
			if (video_pkt.pts() != AV_NOPTS_VALUE) {
				video_pkt.pts(av_rescale_q(video_pkt.pts(), video_c.time_base(), video_st.time_base()));
			}
			if (video_pkt.dts() != AV_NOPTS_VALUE) {
				video_pkt.dts(av_rescale_q(video_pkt.dts(), video_c.time_base(), video_st.time_base()));
			}
		}
		picture.pts(picture.pts() + 1); // magic required by libx264
		avformat.av_interleaved_write_frame(oc, video_pkt);
		av_packet_unref(video_pkt);
        if (av_log_get_level() >= AV_LOG_INFO) {
			av_dump_format(oc, 0, filename, 1);
		}
	} catch (Exception e) {
		LOGGER.error("=> error: ",e);
	} finally {
		recorder.close();
	}

=================== log ===================== filename: D:\video\fengmian\111.mp4, index: 2 [libx264 @ 0000000022c9ca40] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0000000022c9ca40] profile High, level 4.0, 4:2:0, 8-bit [libx264 @ 0000000022c9ca40] 264 - core 159 - H.264/MPEG-4 AVC codec - Copyleft 2003-2019 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=18 lookahead_threads=3 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=abr mbtree=1 bitrate=400 ratetol=1.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00 Output #0, mp4, to 'D:\video\fengmian\111.mp4': Metadata: encoder : Lavf58.29.100 Stream #0:0: Video: h264 (Constrained Baseline) (avc1 / 0x31637661), yuv420p, 1920x1080, q=2-31, 400 kb/s, 25 fps, 12800 tbn, 25 tbc Metadata: my_title2 : my_value2 Stream #0:1: Audio: mp3 (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 192 kb/s [swscaler @ 000000002641b040] Warning: data is not aligned! This can lead to a speed loss [swscaler @ 000000005fdb5ac0] deprecated pixel format used, make sure you did set range correctly [mp4 @ 0000000022c974c0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 94720 >= 0 Output #0, mp4, to 'D:\video\fengmian\111.mp4': Metadata: encoder : Lavf58.29.100 Stream #0:0: Video: h264 (Constrained Baseline) (avc1 / 0x31637661), yuv420p, 1920x1080, q=2-31, 400 kb/s, 25 fps, 12800 tbn, 25 tbc Metadata: my_title2 : my_value2 Stream #0:1: Audio: mp3 (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 192 kb/s Stream #0:2: Video: mjpeg, yuvj444p, 1920x1080, q=2-31, 400 kb/s, 30 fps, 30 tbn, 30 tbc (attached pic) Metadata: my_title : my_value my_title1 : my_value1 [libx264 @ 0000000022c9ca40] frame I:1 Avg QP:33.69 size: 51776 [libx264 @ 0000000022c9ca40] frame P:63 Avg QP:28.63 size: 4139 [libx264 @ 0000000022c9ca40] frame B:186 Avg QP:40.11 size: 166 [libx264 @ 0000000022c9ca40] consecutive B-frames: 0.8% 0.0% 0.0% 99.2% [libx264 @ 0000000022c9ca40] mb I I16..4: 15.6% 69.6% 14.7% [libx264 @ 0000000022c9ca40] mb P I16..4: 0.0% 0.4% 0.0% P16..4: 6.8% 0.6% 0.9% 0.0% 0.0% skip:91.3% [libx264 @ 0000000022c9ca40] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 2.2% 0.0% 0.0% direct: 0.0% skip:97.8% L0: 0.7% L1:99.3% BI: 0.0% [libx264 @ 0000000022c9ca40] final ratefactor: 30.00 [libx264 @ 0000000022c9ca40] 8x8 transform intra:74.5% inter:66.6% [libx264 @ 0000000022c9ca40] coded y,uvDC,uvAC intra: 53.1% 32.6% 5.4% inter: 0.9% 0.9% 0.1% [libx264 @ 0000000022c9ca40] i16 v,h,dc,p: 11% 48% 7% 33% [libx264 @ 0000000022c9ca40] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 15% 20% 25% 6% 8% 5% 8% 5% 8% [libx264 @ 0000000022c9ca40] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 20% 22% 17% 8% 10% 6% 8% 3% 5% [libx264 @ 0000000022c9ca40] i8c dc,h,v,p: 69% 23% 6% 2% [libx264 @ 0000000022c9ca40] Weighted P-Frames: Y:0.0% UV:0.0% [libx264 @ 0000000022c9ca40] ref P L0: 87.8% 6.2% 4.2% 1.8% [libx264 @ 0000000022c9ca40] ref B L0: 73.7% 26.3% [libx264 @ 0000000022c9ca40] ref B L1: 81.0% 19.0% [libx264 @ 0000000022c9ca40] kb/s:274.65