Rare bird has long been considered an important in the field of airport security,biological conservation,environmental monitoring,and so on.With the development and popularization of IOT-based video surveillance,all d...Rare bird has long been considered an important in the field of airport security,biological conservation,environmental monitoring,and so on.With the development and popularization of IOT-based video surveillance,all day and weather unattended bird monitoring becomes possible.However,the current mainstream bird recognition methods are mostly based on deep learning.These will be appropriate for big data applications,but the training sample size for rare bird is usually very short.Therefore,this paper presents a new sparse recognition model via improved part detection and our previous dictionary learning.There are two achievements in our work:(1)after the part localization with selective search,the gist feature of all bird image parts will be fused as data description;(2)the fused gist feature needs to be learned through our proposed intraclass dictionary learning with regularized K-singular value decomposition.According to above two innovations,the rare bird sparse recognition will be implemented by solving one l1-norm optimization.In the experiment with Caltech-UCSD Birds-200-2011 dataset,results show the proposed method can have better recognition performance than other SR methods for rare bird task with small sample size.展开更多
针对多物种鸟声识别中多物种鸟声样本不足的问题,尝试采用单物种鸟声样本训练多物种鸟声识别模型,并提出一种基于特征迁移的多物种鸟声识别方法。该方法引入特征迁移学习算法,利用最大均值差异(Maximum mean discrepancy,MMD)度量鸟声...针对多物种鸟声识别中多物种鸟声样本不足的问题,尝试采用单物种鸟声样本训练多物种鸟声识别模型,并提出一种基于特征迁移的多物种鸟声识别方法。该方法引入特征迁移学习算法,利用最大均值差异(Maximum mean discrepancy,MMD)度量鸟声样本特征分布差异,将不同分布的单物种鸟声和多物种鸟声的音频特征映射为同分布的潜在音频特征,再基于同分布的音频特征构造识别模型。使得单物种鸟声样本训练的识别模型也能够适用于多物种鸟声识别。在自然形成的多物种鸟声数据集上,算法在4项多标记评价指标上都取得了较好的识别效果;在人工构造的多物种鸟声数据集上对比试验表明,基于特征迁移的识别算法在单个物种上的正确识别率相较于对比算法最高提升了20%。展开更多
文摘【目的】深度学习在鸟类物种识别的应用是目前的研究热点,为了进一步提高识别效果,提出一种基于鸟鸣声的Chirplet语图特征和深度卷积神经网络的鸟类物种识别方法。【方法】引入线性调频小波变换(Chirplet transform,CT)计算鸟鸣声信号的语图,输入深度卷积神经网络VGG16模型中,通过对语图进行分类实现鸟类物种的识别。以北京市松山国家自然保护区实地采集的18种鸟类为研究对象,利用Chirplet变换、短时傅里叶变换(short-time fourier transform,STFT)和梅尔频率倒谱变换(Mel frequency cepstrum transform,MFCT)计算得到3个不同的语图样本集,对比分别采用不同的语图样本集作为输入时鸟类物种识别模型的性能。【结果】结果表明:Chirplet语图作为输入时,测试集的平均识别准确率(mean average precision,MAP)达到0.987 1,相对于其他两种输入,得到了更高的MAP值,而且在训练时达到最大MAP值的迭代次数最小。【结论】采用不同的语图特征作为输入,直接影响深度学习模型的分类性能。本文计算的Chirplet语图的鸣声区域相比STFT语图和Mel语图更为集中,特征更明显。因此,Chirplet语图更适合于基于VGG16模型的鸟类物种识别,可以得到更高的MAP值和更快的识别效率。
文摘Rare bird has long been considered an important in the field of airport security,biological conservation,environmental monitoring,and so on.With the development and popularization of IOT-based video surveillance,all day and weather unattended bird monitoring becomes possible.However,the current mainstream bird recognition methods are mostly based on deep learning.These will be appropriate for big data applications,but the training sample size for rare bird is usually very short.Therefore,this paper presents a new sparse recognition model via improved part detection and our previous dictionary learning.There are two achievements in our work:(1)after the part localization with selective search,the gist feature of all bird image parts will be fused as data description;(2)the fused gist feature needs to be learned through our proposed intraclass dictionary learning with regularized K-singular value decomposition.According to above two innovations,the rare bird sparse recognition will be implemented by solving one l1-norm optimization.In the experiment with Caltech-UCSD Birds-200-2011 dataset,results show the proposed method can have better recognition performance than other SR methods for rare bird task with small sample size.
文摘针对多物种鸟声识别中多物种鸟声样本不足的问题,尝试采用单物种鸟声样本训练多物种鸟声识别模型,并提出一种基于特征迁移的多物种鸟声识别方法。该方法引入特征迁移学习算法,利用最大均值差异(Maximum mean discrepancy,MMD)度量鸟声样本特征分布差异,将不同分布的单物种鸟声和多物种鸟声的音频特征映射为同分布的潜在音频特征,再基于同分布的音频特征构造识别模型。使得单物种鸟声样本训练的识别模型也能够适用于多物种鸟声识别。在自然形成的多物种鸟声数据集上,算法在4项多标记评价指标上都取得了较好的识别效果;在人工构造的多物种鸟声数据集上对比试验表明,基于特征迁移的识别算法在单个物种上的正确识别率相较于对比算法最高提升了20%。
