* wip
* make separate score func
* n4ot g
* clean up
* remove
* simplify
* b2b
* more than 0
* this is fine
* led
* balance costs
* clean up
* no if tici
* box view
* new baselines
* Revert "new baselines"
This reverts commit f7a5d059ed.
* Revert "box view"
This reverts commit a57924be36.
* maximize dcg
Co-authored-by: Comma Dev1ce <device@comma.ai>
old-commit-hash: bc8e2032f7
* ev has different scales
* fix initial gradient
* fix highlight weirdness
* try smooth set of gains
* delay
* add gain idx
* oops
* set different min dc
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: c7a0f23b45
* start porting OS04C10
* something
* is the pll why this doesn't work
* understand plls, still doesn't work
* work
* weee something
* working?
* timing
* encoderd works with less cameras
* 1928
* flip image
* color balance
* adjust black level
* extra height maybe
* cleanups
* clean up sensor i2c
* sensors
* approx 20fps
* remove mirror
* 50ms, no fsin yet
* remove imx390 support
* some attempt at AE
* linearize the response
* OX changes (#25697)
* organize
* wb
* best effort but probably messed up by artifacts
* multicam sync
Co-authored-by: Comma Device <device@comma.ai>
* clean up
* more
* fix multiexposure
* start porting OS04C10
* something
* is the pll why this doesn't work
* understand plls, still doesn't work
* work
* weee something
* working?
* timing
* encoderd works with less cameras
* 1928
* flip image
* color balance
* adjust black level
* extra height maybe
* cleanups
* clean up sensor i2c
* sensors
* approx 20fps
* remove mirror
* 50ms, no fsin yet
* remove imx390 support
* some attempt at AE
* linearize the response
* OX changes (#25697)
* organize
* wb
* best effort but probably messed up by artifacts
* multicam sync
Co-authored-by: Comma Device <device@comma.ai>
* clean up
* more
* fix multiexposure
* unbroken AE
* oops
* sort of good AE
* both should work 1
* open then init
* fix debayer
* rename
* fix test build
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: ZwX1616 <zwx1616@gmail.com>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
old-commit-hash: aea1a0d5e6
* pixclk 88mhz but frame time the same
* scale integration time
* 22.8 ms
* 15.18 ms
* fix exposure
* fix glitching, 18.9 ms
* set both to min
* faster pixclk = more power
* should pass CI
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: Willem Melching <willem.melching@gmail.com>
old-commit-hash: 7c74ab8992
* support disabling the cameras
* disable instead of only. reduce camera startup time
* cleanups
* make all disables work
* add more logging to buffer creation
* make disable work
* disable on sensor probe failed
* tested, fix print
* tolerate sensor failure onroad
* enables should be honored in public methods only
* comments and whitespace
* debug starting sensor
* bring clear_req_queue into c++, add logging for error cases
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 10d4766f76
* something is output
* min stuff
* visible picture
* pics look good
* maybe
* whole sensor
* fix all cameras
* support both cameras
* autoexposure for imx390
* fix imx390 blacklevel
* touchups
* put gain in db scale
* inline and fix max exposure
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 5a11101bcf
* AE improvements
* boardd: also use gain to compute IR brightness
* use default rect for DM autoexposure
* more smooth
* whitespace
* camerad cpu usage
* hcg on is slightly better for noise
* hysteris around high conversion gain
* improve i2c timing
* use AB contexts
* HCG default off
* run at 10 hz
* stay in context A for now
* remove ae thread
* wait till next frame is started before sending i2c
* back at 20fps
* add comment and filter across 3 evs
* remove context switch code
* tuning
* recomened without HCG is 0.8x
old-commit-hash: 25de93d133
* Move MCLK freq
* change PLL settings to compensate
* messed that up
* undo extclk change, move the internal freq. Does mean pixclk is decreased from 88MHz to 80MHz though
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 18ab822213
* protect highlights
* fix modeld scale factor
* rewrite logic for accurate and smooth AE
* fix condition
* tune speed
* move to qcom2
* not exactly 2x
* avoid hunting due to ettr policy
* tune to new curve
* gain kickdowns
* log params
* 4x legroom
* no limit needed here
* simple lowpass
* tweak
* pin to a remote core
* speedup AE and lower night exp
* this curve makes more sense
* tuning from fleet data
* fix ui
* only qcom2
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 00b642146f
* nerf highlights
* prioritize less noise
* no overhead
* make focus easier
* cant finetune under high gain
* add some comments
* inspired by xx mindset
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 911206fc41
* capnparm
* building in progress
* scons build works
* that script fixes opencl
* start new camera code
* includes and more camera scripts
* control c works now
* no device control yet
* phy too
* just one camera for now
* fix capnparm
* hmm, the inits are needed
* more cameras
* link stop start
* doesn't work yet
* fix ion on qcom2
* start poll ish
* 4 pictures and done
* no jpeg
* it works to picture
* destroy sync obj
* both work for now
* defined QCOM2
* fix fd leak
* run modeld
* 10 bit mode
* real frame stride
* needs digital gain
* dnew
* no color correcting on new
* that snpe doesn't work
* qcom2 gate
* cleanups
* oops, fix aarch64 detector
* update cereal
* modeld works with SNPE
* fix driver monitoring model
Co-authored-by: Tici <robbe@comma.ai>
old-commit-hash: 8db0993663
Adeeb Shihadeh
Dean Lee
ZwX1616
Robbe Derks
George Hotz
Willem Melching
Adeeb