Deep map prediction plays a crucial role in comprehending the three-dimensional structure of a scene, which is essential for enabling mobile robots to navigate autonomously and avoid obstacles in complex environments. However, most existing depth estimation algorithms based on deep neural networks rely heavily on specific datasets, resulting in poor resistance to model interference. To address this issue, this paper proposes and implements an optimized monocular image depth estimation algorithm based on conditional generative adversarial networks. The goal is to overcome the limitations of insufficient training data diversity and overly blurred depth estimation contours in current monocular image depth estimation algorithms based on generative adversarial networks. The proposed algorithm employs an enhanced conditional generative adversarial network model with a generator that adopts a network structure similar to UNet and a novel feature upsampling module. The discriminator uses a multi-layer patchGAN conditional discriminator and incorporates the original depth map as input to effectively utilize prior knowledge. The loss function combines the least squares loss function and the L1 loss function. Compared to traditional depth estimation algorithms, the proposed optimization algorithm can effectively restore image contour information and enhance the visualization capability of depth prediction maps. Experimental results demonstrate that our method can expedite the convergence of the model on NYU-V2 and Make3D datasets, and generate predicted depth maps that contain more details and clearer object contours.
7 March 2022 in International Journal of Intelligent Systems
With the continuous expansion of software scale and the continuous complexity of software functions, abnormal parameter configuration often brings adverse effects to the software system and even leads to system failure. Therefore, a method is needed to detect whether the parameter configuration is correct. Most of the current configuration errors detection methods focus on the passive diagnosis after the system failure, which cannot solve the potential delay problem of configuration error. This paper proposes an automatic real-time detection method of software configuration errors, in which the configuration items are classified based on the fine-grained configuration item types and related syntax patterns, and the configuration constraint rule base is generated. Then, the real-time exception detection of configuration update operation is realized by using the file operation monitoring function. The experimental results show that this method can accurately classify the types of configuration items and verify the effectiveness of detecting software configuration update exceptions in real time through the constraint rule base. The classification accuracy reaches up to 90.4% on MySQL and 87.4% on Apache.