This paper introduces a deep learning methodology for analyzing audience engagement in online video events. The proposed deep learning framework consists of six layers and starts with keyframe extraction from the video stream and the participants’ face detection. Subsequently, the head pose and emotion per participant are estimated using the HopeNet and JAA-Net deep architectures. Complementary to video analysis, the audio signal is also processed using a neural network that follows the DenseNet-121 architecture. Its purpose is to detect events related to audience engagement, including speech, pauses, and applause. With the combined analysis of video and audio streams, the interest and attention of each participant are inferred more accurately. An experimental evaluation is performed on a newly generated dataset consisting of recordings from online video events, where the proposed framework achieves promising results. Concretely, the F1 scores were 79.21% for interest estimation according to pose, 65.38% for emotion estimation, and 80% for sound event detection. The proposed framework has applications in online educational events, where it can help tutors assess audience engagement and comprehension while hinting at points in their lectures that may require further clarification. It is effective for video streaming platforms that want to provide video recommendations to online users according to audience engagement.

Photogrammetry is the process of creating three-dimensional (3D) reconstructions from two-dimensional images. In this paper, a novel method is introduced that significantly enhances 3D reconstruction by improving image quality through a combination of RGB stretching, Contrast Limited Adaptive Histogram Equalization (CLAHE), and colormaps. This approach effectively increases the number of keypoints and matches between images, resulting in more accurate and detailed 3D reconstructions. Additionally, a heuristic methodology is proposed to identify the optimal colormaps for each dataset based on keypoint matches between image pairs. This approach saves valuable time by recommending the most effective colormaps, eliminating the need to test each individually. A new dataset comprising two real-world image collections from underwater cultural heritage sites is presented to validate the algorithm, characterized by challenging environments such as low visibility and varying lighting conditions. The limitations of existing techniques are addressed by this method, providing a robust solution for enhancing image quality in demanding underwater scenarios. Experimental results show that image enhancement can lead to a 7.91% and 11.4% improvement, and the enhancement fusion with colormaps improves reconstruction accuracy by 10.82% and 64.11%. These findings render the proposed methodology a promising tool for 3D reconstruction in challenging environments, like underwater.