Hu Qiao

No Thumbnail Available
Last Name
Hu
First Name
Qiao
ORCID

Filters

2006 - 2008 5
3 1 1
5
Reset filters

Settings

Search Results

Now showing 1 - 5 of 5
  • Article
    Accurate automatic quantification of taxa-specific plankton abundance using dual classification with correction
    (Inter-Research, 2006-01-11) Hu, Qiao ; Davis, Cabell S.
    Optical imaging samplers are becoming widely used in plankton ecology, but image analysis methods have lagged behind image acquisition rates. Automated methods for analysis and recognition of plankton images have been developed, which are capable of real-time processing of incoming image data into major taxonomic groups. The limited accuracy of these methods can require significant manual post-processing to correct the automatically generated results, in order to obtain accurate estimates of plankton abundance patterns. We present here a dual-classification method in which each plankton image is first identified using a shaped-based feature set and a neural network classifier, and then a second time using a texture-based feature set and a support vector machine classifier. The plankton image is considered to belong to a given taxon only if the 2 identifications agree; otherwise it is labeled as unknown. This dual-classification method greatly reduces the false positive rate, and thus gives better abundance estimation in regions of low relative abundance. A confusion matrix is computed from a set of training images in order to determine the detection and false positives rates. These rates are used to correct abundances estimated from the automatic classification results. Aside from the manual sorting required to generate the initial training set of images, this dual-classification method is fully automatic and does not require subsequent manual correction of automatically sorted images. The resulting abundances agree closely with those obtained using manually sorted results. A set of images from a Video Plankton Recorder was used to evaluate this method and compare it with previously reported single-classifier results for major taxa.
  • Article
    A simplified age-stage model for copepod population dynamics
    (Inter-Research, 2008-05-22) Hu, Qiao ; Davis, Cabell S. ; Petrik, Colleen M.
    Complex 3D biological-physical models are becoming widely used in marine and freshwater ecology. These models are highly valued synthesizing tools because they provide insights into complex dynamics that are difficult to understand using purely empirical methods or theoretical analytical models. Of particular interest has been the incorporation of concentration-based copepod population dynamics into 3D physical transport models. These physical models typically have large numbers of grid points and therefore require a simplified biological model. However, concentration-based copepod models have used a fine resolution age-stage structure to prevent artificially short generation times, known as numerical ‘diffusion.’ This increased resolution has precluded use of age-stage structured copepod models in 3D physical models due to computational constraints. In this paper, we describe a new method, which tracks the mean age of each life stage instead of using age classes within each stage. We then compare this model to previous age-stage structured models. A probability model is developed with the molting rate derived from the mean age of the population and the probability density function (PDF) of molting. The effects of temperature and mortality on copepod population dynamics are also discussed. The mean-age method effectively removes the numerical diffusion problem and reproduces observed median development times (MDTs) without the need for a high-resolution age-stage structure. Thus, it is well-suited for finding solutions of concentration-based zooplankton models in complex biological-physical models.
  • Article
    RAPID : research on automated plankton identification
    (Oceanography Society, 2007-06) Benfield, Mark C. ; Grosjean, Philippe ; Culverhouse, Phil F. ; Irigoien, Xabier ; Sieracki, Michael E. ; Lopez-Urrutia, Angel ; Dam, Hans G. ; Hu, Qiao ; Davis, Cabell S. ; Hansen, Allen ; Pilskaln, Cynthia H. ; Riseman, Edward M. ; Schultz, Howard ; Utgoff, Paul E. ; Gorsky, Gabriel
    When Victor Hensen deployed the first true plankton1 net in 1887, he and his colleagues were attempting to answer three fundamental questions: What planktonic organisms are present in the ocean? How many of each type are present? How does the plankton’s composition change over time? Although answering these questions has remained a central goal of oceanographers, the sophisticated tools available to enumerate planktonic organisms today offer capabilities that Hensen probably could never have imagined.
  • Preprint
    Focus detection from digital in-line holograms based on spectral l1 norms
    ( 2007-05-16) Li, Weichang ; Loomis, Nicholas C. ; Hu, Qiao ; Davis, Cabell S.
    In this paper a rapid focus detection technique is developed for objects imaged using digital in-line holograms. It differs from previous approaches in that it is based directly on the spectral content of the object images and does not need a full reconstruction of the actual images. It is based on new focus metrics defined as the l1 norms of the object spectral components associated with the real and imaginary parts of the reconstruction kernel. Furthermore, these l1 norms can be computed efficiently in the frequency domain using a polar coordinate system, yielding a drastic speedup of about two orders of magnitude compared with image-based focus detection. The subsequent reconstruction, when done selectively over these detected focus distances, leads to significant computational savings. Focus detection results from holograms of plankton are demonstrated showing that the technique is both accurate and robust.
  • Thesis
    Application of statistical learning theory to plankton image analysis
    (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2006-06) Hu, Qiao
    A fundamental problem in limnology and oceanography is the inability to quickly identify and map distributions of plankton. This thesis addresses the problem by applying statistical machine learning to video images collected by an optical sampler, the Video Plankton Recorder (VPR). The research is focused on development of a real-time automatic plankton recognition system to estimate plankton abundance. The system includes four major components: pattern representation/feature measurement, feature extraction/selection, classification, and abundance estimation. After an extensive study on a traditional learning vector quantization (LVQ) neural network (NN) classifier built on shape-based features and different pattern representation methods, I developed a classification system combined multi-scale cooccurrence matrices feature with support vector machine classifier. This new method outperforms the traditional shape-based-NN classifier method by 12% in classification accuracy. Subsequent plankton abundance estimates are improved in the regions of low relative abundance by more than 50%. Both the NN and SVM classifiers have no rejection metrics. In this thesis, two rejection metrics were developed. One was based on the Euclidean distance in the feature space for NN classifier. The other used dual classifier (NN and SVM) voting as output. Using the dual-classification method alone yields almost as good abundance estimation as human labeling on a test-bed of real world data. However, the distance rejection metric for NN classifier might be more useful when the training samples are not “good” ie, representative of the field data. In summary, this thesis advances the current state-of-the-art plankton recognition system by demonstrating multi-scale texture-based features are more suitable for classifying field-collected images. The system was verified on a very large realworld dataset in systematic way for the first time. The accomplishments include developing a multi-scale occurrence matrices and support vector machine system, a dual-classification system, automatic correction in abundance estimation, and ability to get accurate abundance estimation from real-time automatic classification. The methods developed are generic and are likely to work on range of other image classification applications.