**9. Evaluation**

In this section, we introduce the evaluation of the investigated networks by processing 10 images with different gamma values. Images are indicated in the tables below with numbers from 0 to 9. We use score values to compare the different networks to indicate the probability of the proper classification. Their score value is shown in the contingency tables. Besides this, the bottom row contains the average score value related to the different images.

Mask R-CNN with AlexNet Backbone.

**Table 6.** Top score of the 10 images represented by numbers 0 to 9 with different gamma values (*γ*) while using Mask R-CNN with backbone Alex Net.


Mask R-CNN with MobileNet V2 Backbone.


**Table 7.** Top score of the 10 images with different gamma values (*γ*) while using Mask R-CNN with backbone Mobile Net V2.

Mask R-CNN with ResNet50 Backbone.

**Table 8.** Top score of the 10 images with different gamma values (*γ*) while using Mask R-CNN with backbone ResNet 50.


Mask R-CNN with VGG11 Backbone.


**Table 9.** Top score of the 10 images with different gamma values (*γ*) while using Mask R-CNN with backbone VGG11.

Mask R-CNN with VGG13 Backbone.

**Table 10.** Top score of the 10 images with different gamma values (*γ*) while using Mask R-CNN with backbone VGG13.


Mask R-CNN with VGG16 Backbone.

As shown in the heat map below, Mask R-CNN with Resnet 50 had the best performance in all scenarios. If the gamma was 1, the average score value was 99.68%.

As the intensity of the image changes from dark to bright section, the scores of the ResNet increases until gamma 1. Generally, ResNet50 based Mask R-CNN model performs well in all scenarios. Even if the images become brighter, the score of the ResNet 50 decreases much slower than the other models (see Table 12).


**Table 11.** Top score of the 10 images with different gamma values (*γ*) while using Mask R-CNN with backbone VGG16.

**Table 12.** Heat map of the Mask R-CNN models with respect to different values of gamma (*γ*). The colour of the cells changes from green to red, where green indicates high values and red indicates low values.


In our study, we tested the models on a custom dataset. However, in real life, the system must deal with real-time datasets. Accordingly, in the future, we are planning to test the KITTI dataset. It contains 3D data involving Lidar sensor data, images, etc.

We found a robust and flexible detection model (Mask R-CNN) that can perform well in any scenario, whether it is day or night. In future research steps, we are going to investigate images from rainy and smoky conditions.

Furthermore, self-driving cars are expected to be equipped with high-resolution cameras recording gamma value as well. Following this, it seems reasonable to use the automatic gamma correction method to improve the efficiency of the instance detection process in different driving conditions.
