A Spatial-Spectral Classification Method Based on Deep Learning for Controlling Pelagic Fish Landings in Chile.

Fishing has provided mankind with a protein-rich source of food and labor, allowing for the development of an important industry, which has led to the overexploitation of most targeted fish species. The sustainable management of these natural resources requires effective control of fish landings and, therefore, an accurate calculation of fishing quotas. This work proposes a deep learning-based spatial-spectral method to classify five pelagic species of interest for the Chilean fishing industry, including the targeted Engraulis ringens, Merluccius gayi, and Strangomera bentincki and non-targeted Normanichthtys crockeri and Stromateus stellatus fish species. This proof-of-concept method is composed of two channels of a convolutional neural network (CNN) architecture that processes the Red-Green-Blue (RGB) images and the visible and near-infrared (VIS-NIR) reflectance spectra of each species. The classification results of the CNN model achieved over 94% in all performance metrics, outperforming other state-of-the-art techniques. These results support the potential use of the proposed method to automatically monitor fish landings and, therefore, ensure compliance with the established fishing quotas.

Digital Classification of Chilean Pelagic Species in Fishing Landing Lines.

Fishing landings in Chile are inspected to control fisheries that are subject to catch quotas. The control process is not easy since the volumes extracted are large and the numbers of landings and artisan shipowners are high. Moreover, the number of inspectors is limited, and a non-automated method is utilized that normally requires months of training. In this work, we propose, design, and implement an automated fish landing control system. The system consists of a custom gate with a camera array and controlled illumination that performs automatic video acquisition once the fish landing starts. The imagery is sent to the cloud in real time and processed by a custom-designed detection algorithm based on deep convolutional networks. The detection algorithm identifies and classifies different pelagic species in real time, and it has been tuned to identify the specific species found in landings of two fishing industries in the Biobío region in Chile. A web-based industrial software was also developed to display a list of fish detections, record relevant statistical summaries, and create landing reports in a user interface. All the records are stored in the cloud for future analyses and possible Chilean government audits. The system can automatically, remotely, and continuously identify and classify the following species: anchovy, jack mackerel, jumbo squid, mackerel, sardine, and snoek, considerably outperforming the current manual procedure.

Three-dimensional point spread function estimation method for mid-wave infrared microscope imaging.

A three-dimensional point spread function experimental estimation method based on the system's focal plane array spatial local impulse response of a mid-wave infrared microscope is presented. The method uses several out-of-focus two-dimensional point spread function planes to achieve a single three-dimensional point spread function of the whole microscope's optical spreading, expanding the limits of infrared optical technology by one dimension. This technique includes stages of image acquisition, nonuniformity correction, filtering, and multi-planar reconstruction steps, and its effectiveness is demonstrated on biological sample image restoration by means of a multi-planar refocusing application.

Infrared light field imaging system free of fixed-pattern noise.

Digital photonic sensors have greatly evolved to maximize sensitivity and spatial, spectral, and temporal imaging resolution. For low-energy photons, new designs have generated new types of noise that degrade the formed-image signal-to-noise ratio to values lower than 1. Fixed-pattern noise (FPN), which is produced by the non-uniform focal-plane-array optoelectronics response, is an ill-posed problem in infrared and hyperspectral imaging science. Here, we experimentally show that the FPN behaves as an object at a depth of infinity when a light field is captured by an imaging system. The proposed method is based on the capture of the light field of a scene and digital refocusing to any nearby objects in the scene. Unlike standard techniques for FPN reduction, our method does not require knowledge of the physical parameters of the optoelectronic transducer, the motion scene, or the presence of off-line blackbody sources. The ability of the proposed method to reduce FPN is measured by evaluating the structural similarity (SSIM) index employing a blackbody-based FPN reduction technique as a reference. This new interpretation of the FPN opens avenues to create new cameras for low-energy photons with the ability to perform denoising by digital refocusing.

Noise-cancellation-based nonuniformity correction algorithm for infrared focal-plane arrays.

The spatial fixed-pattern noise (FPN) inherently generated in infrared (IR) imaging systems compromises severely the quality of the acquired imagery, even making such images inappropriate for some applications. The FPN refers to the inability of the photodetectors in the focal-plane array to render a uniform output image when a uniform-intensity scene is being imaged. We present a noise-cancellation-based algorithm that compensates for the additive component of the FPN. The proposed method relies on the assumption that a source of noise correlated to the additive FPN is available to the IR camera. An important feature of the algorithm is that all the calculations are reduced to a simple equation, which allows for the bias compensation of the raw imagery. The algorithm performance is tested using real IR image sequences and is compared to some classical methodologies.

Multimodel Kalman filtering for adaptive nonuniformity correction in infrared sensors.

We present an adaptive technique for the estimation of nonuniformity parameters of infrared focal-plane arrays that is robust with respect to changes and uncertainties in scene and sensor characteristics. The proposed algorithm is based on using a bank of Kalman filters in parallel. Each filter independently estimates state variables comprising the gain and the bias matrices of the sensor, according to its own dynamic-model parameters. The supervising component of the algorithm then generates the final estimates of the state variables by forming a weighted superposition of all the estimates rendered by each Kalman filter. The weights are computed and updated iteratively, according to the a posteriori-likelihood principle. The performance of the estimator and its ability to compensate for fixed-pattern noise is tested using both simulated and real data obtained from two cameras operating in the mid- and long-wave infrared regime.

Scene-based nonuniformity correction for focal plane arrays by the method of the inverse covariance form.

What is to our knowledge a new scene-based algorithm for nonuniformity correction in infrared focal-plane array sensors has been developed. The technique is based on the inverse covariance form of the Kalman filter (KF), which has been reported previously and used in estimating the gain and bias of each detector in the array from scene data. The gain and the bias of each detector in the focal-plane array are assumed constant within a given sequence of frames, corresponding to a certain time and operational conditions, but they are allowed to randomly drift from one sequence to another following a discrete-time Gauss-Markov process. The inverse covariance form filter estimates the gain and the bias of each detector in the focal-plane array and optimally updates them as they drift in time. The estimation is performed with considerably higher computational efficiency than the equivalent KF. The ability of the algorithm in compensating for fixed-pattern noise in infrared imagery and in reducing the computational complexity is demonstrated by use of both simulated and real data.

Kalman filtering for adaptive nonuniformity correction in infrared focal-plane arrays.

A novel statistical approach is undertaken for the adaptive estimation of the gain and bias nonuniformity in infrared focal-plane array sensors from scene data. The gain and the bias of each detector are regarded as random state variables modeled by a discrete-time Gauss-Markov process. The proposed Gauss-Markov framework provides a mechanism for capturing the slow and random drift in the fixed-pattern noise as the operational conditions of the sensor vary in time. With a temporal stochastic model for each detector's gain and bias at hand, a Kalman filter is derived that uses scene data, comprising the detector's readout values sampled over a short period of time, to optimally update the detector's gain and bias estimates as these parameters drift. The proposed technique relies on a certain spatiotemporal diversity condition in the data, which is satisfied when all detectors see approximately the same range of temperatures within the periods between successive estimation epochs. The performance of the proposed technique is thoroughly studied, and its utility in mitigating fixed-pattern noise is demonstrated with both real infrared and simulated imagery.