The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Visant les inconvénients de l'algorithme de correction de non-uniformité (NUC) des réseaux neuronaux traditionnels tels que la convergence lente, la faible précision de correction et la difficulté à répondre aux exigences des applications d'ingénierie en temps réel du système d'imagerie infrarouge, un algorithme NUC amélioré pour les réseaux à plan focal infrarouge (IRFPA) basé sur un réseau neuronal est proposé. L'algorithme est basé sur une réponse linéaire du détecteur, et afin de réaliser une convergence rapide et synchronisée des paramètres de correction, chaque donnée d'image originale est normalisée à une valeur proche de un. Les résultats expérimentaux montrent que la méthode a une vitesse de convergence plus rapide et un meilleur effet de vision que les algorithmes traditionnels, et qu'elle est mieux appliquée dans des projets pratiques.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Shao-sheng DAI, Tian-qi ZHANG, "An Improved Non-uniformity Correction Algorithm for IRFPA Based on Neural Network" in IEICE TRANSACTIONS on Electronics,
vol. E92-C, no. 5, pp. 736-739, May 2009, doi: 10.1587/transele.E92.C.736.
Abstract: Aiming at traditional neural networks non-uniformity correction (NUC) algorithm's disadvantages such as slow convergence, low correction precision and difficulty to meet the real-time engineering application requirements of infrared imaging system, an improved NUC algorithm for infrared focal plane arrays (IRFPA) based on neural network is proposed. The algorithm is based on linear response of detector, and in order to realize fast and synchronization convergence of correction parameters the each original image data is normalized to a value close to one. Experimental results show the method has the faster convergence speed and better vision effect than the traditional algorithms, and it is better applied in practical projects.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/transele.E92.C.736/_p
Copier
@ARTICLE{e92-c_5_736,
author={Shao-sheng DAI, Tian-qi ZHANG, },
journal={IEICE TRANSACTIONS on Electronics},
title={An Improved Non-uniformity Correction Algorithm for IRFPA Based on Neural Network},
year={2009},
volume={E92-C},
number={5},
pages={736-739},
abstract={Aiming at traditional neural networks non-uniformity correction (NUC) algorithm's disadvantages such as slow convergence, low correction precision and difficulty to meet the real-time engineering application requirements of infrared imaging system, an improved NUC algorithm for infrared focal plane arrays (IRFPA) based on neural network is proposed. The algorithm is based on linear response of detector, and in order to realize fast and synchronization convergence of correction parameters the each original image data is normalized to a value close to one. Experimental results show the method has the faster convergence speed and better vision effect than the traditional algorithms, and it is better applied in practical projects.},
keywords={},
doi={10.1587/transele.E92.C.736},
ISSN={1745-1353},
month={May},}
Copier
TY - JOUR
TI - An Improved Non-uniformity Correction Algorithm for IRFPA Based on Neural Network
T2 - IEICE TRANSACTIONS on Electronics
SP - 736
EP - 739
AU - Shao-sheng DAI
AU - Tian-qi ZHANG
PY - 2009
DO - 10.1587/transele.E92.C.736
JO - IEICE TRANSACTIONS on Electronics
SN - 1745-1353
VL - E92-C
IS - 5
JA - IEICE TRANSACTIONS on Electronics
Y1 - May 2009
AB - Aiming at traditional neural networks non-uniformity correction (NUC) algorithm's disadvantages such as slow convergence, low correction precision and difficulty to meet the real-time engineering application requirements of infrared imaging system, an improved NUC algorithm for infrared focal plane arrays (IRFPA) based on neural network is proposed. The algorithm is based on linear response of detector, and in order to realize fast and synchronization convergence of correction parameters the each original image data is normalized to a value close to one. Experimental results show the method has the faster convergence speed and better vision effect than the traditional algorithms, and it is better applied in practical projects.
ER -