Video frame freezing is a common artifact which can occur during video content
delivery due to errors in the video coding process, video transmission, storage or
reproduction. This artifact can significantly decrease the end-user Quality of Experience
(QoE). We have developed an efficient no-reference freezing detection algorithm
which has a very high detection rate with a very low rate of false positive detections
for videos with different content and resolution. The optimized implementation of
Intel processor with AVX2 instruction set is proposed along with efficient practical
implementation in FPGA.
****
Grbić, Ratko; Stefanović, Dejan; Vranješ, Mario; Herceg, Marijan
Real‑time video freezing detection for 4K UHD videos // Journal of Real-Time Image
Processing, 17 (2020), 5; 1211-1225 doi:10.1007/s11554-019-00873-y
****