Classification of objects in images with distortions based on a two-stage topological analysis
Annotation
The authors propose a method for automatic classification of spatial objects in images under conditions of a limited data set. The stability of the method to distortions appearing in images due to natural phenomena and partial overlap of urban infrastructure objects is investigated. High classification accuracy, when using existing approaches, requires a large training sample, including data sets with distortions, which significantly increases computational complexity. The paper proposes a method for a two-step topological analysis of images. Topological features are initially extracted by analyzing the image in the brightness range from 0 to 255, and then from 255 to 0. These features complement each other and reflect the topological structure of the object. Under certain deformations and distortions, the object preserves its structure in the form of extracted features. The advantage of the method is a small number of patterns, which reduces the computational complexity of training compared to neural networks. The proposed method is investigated and compared with the modern neural network approach. The study was performed on a DOTA dataset (Dataset for Object deTection in Aerial images) containing images of spatial objects of several classes. In the absence of distortion in the image, the neural network approach showed a classification accuracy of over 98 %, while the proposed method achieved about 82 %. Further distortions such as 90 degree rotation, 50 % narrowing and 50 % edge truncation and their combinations were applied in the experiment. The proposed method showed its robustness and outperformed the neural network approach. In the most difficult combination of the test, the decrease in classification accuracy of the neural network was 46 %, while the described method showed 12 %. The proposed method can be applied in cases with a high probability of distortion in the images. Such distortions arise in the field of geoinformatics when analyzing objects of various scales, under different weather conditions, partial overlap of one object with another, in the presence of shadows, etc. It is possible to use the proposed method in vision systems of industrial enterprises for automatic classification of the parts that belong to superimposed objects.
Keywords
Постоянный URL
Articles in current issue
- A study of a silicone film deposited on quartz glass under laser radiation
- Optical composites based on organic polymers and semiconductor pigments
- A new algorithm for the identification of sinusoidal signal frequency with constant parameters
- A study of silicon p-n structures with mono and multifacial photosensitive surfaces
- Detection of yawning in driver behavior based a convolutional neural network
- A Game Theory approach for communication security and safety assurance in cyber-physical systems with Reputation and Trust-based mechanisms
- A study of the influence of human factors on the speed of urban rail transport
- An algorithm for detecting RFID-duplicates
- Reduction of LSB detectors set with definite reliability
- Dimensionality reduction of the attributes using fuzzy optimized independent component analysis for a Big Data Intrusion Detection System
- An optimal swift key generation and distribution for QKD
- A study of vectorization methods for unstructured text documents in natural language according to their influence on the quality of work of various classifiers
- Recognition the emotional state based on a convolutional neural network
- Intellectualization of personnel development management in high-tech service-oriented companies
- A study of the efficiency of the magnetic compass correction system
- A new analytical model of drain current and small signal parameters for AlGaN-GaN high-electron-mobility transistors
- Imputation and system modeling of acid-base state parameters for different groups of patients
- Construction of movement trajectories for objects based on the Dubins car problem, taking into account constant external influences
- A mathematical model of an epidemic with an arbitrary law of recovery
- Simulation of the pulsed outflow of air and fine powder mixture, partially filling the discharge channel
- Vectorized numerical algorithms for the solution of continuum mechanics problems
- A comparative analysis of computational intelligence algorithms for estimation of LTE channels
- Implementation of a clinical decision support system to improve the medical data quality for hypertensive patients